MIREX Wiki - User contributions [en]

MIREX HOME

2026-03-16T06:00:46Z

Junyan: /* Welcome to MIREX 2026 */

==Welcome to MIREX 2026==

MIREX (Music Information Retrieval Evaluation eXchange) is an annual community evaluation campaign held in conjunction with the [https://ismir.net/ International Society for Music Information Retrieval Conference (ISMIR)]. This year, the conference will be held in [https://ismir2026.ismir.net/ Abu Dhabi, UAE] from November 8–12, 2026, and may include an online component.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Call for Challenges==

We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field. We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2026:Call for Challenges]].

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

===What's new:===

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

Furthermore, all task captains are encouraged to report key resource indicators for each submission, including:

* training data size
* model size
* other computational resources used in model development

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2026.

==Important Dates==

* Challenge proposals due: May 15, 2026
* Notification of acceptance: May 29, 2026
* Submission open: Jul 1, 2026
* Submission close: Oct 1, 2026 (Some tasks may have a different deadline; see task descriptions)
* Result published: Oct 15, 2026 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source evaluation pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2026!

Future MIREX Team, 2026

MIREX 2026 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2026:Call for Challenges

2026-03-16T05:35:49Z

Junyan: /* Deadlines */

MIREX HOME

2026-03-16T05:35:27Z

Junyan: /* Important Dates */

==Welcome to MIREX 2026==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2026.ismir.net/ Abu Dhabi, UAE] from November 8-12, 2026, possibly with an online component.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Call for Challenges==

We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field. We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2026:Call for Challenges]].

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

===What's new:===

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

Furthermore, all task captains are encouraged to report key resource indicators for each submission, including:

* training data size
* model size
* other computational resources used in model development

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2026.

==Important Dates==

* Challenge proposals due: May 15, 2026
* Notification of acceptance: May 29, 2026
* Submission open: Jul 1, 2026
* Submission close: Oct 1, 2026 (Some tasks may have a different deadline; see task descriptions)
* Result published: Oct 15, 2026 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source evaluation pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2026!

Future MIREX Team, 2026

MIREX 2026 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2026:Call for Challenges

2026-03-16T04:53:21Z

Junyan:

2026:Call for Challenges

2026-03-16T04:48:46Z

Junyan: /* Call for Challenge Proposals & Task Captains */

2025:Previous Tasks

2026-03-16T04:47:36Z

Junyan: /* List of Previous Tasks */

==List of Previous Tasks==

This is a list of previous MIREX tasks for reference only.

* [[2025:RenCon]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>
* [[2025:Music Reasoning QA]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2024:Symbolic Music Generation]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang]>
* [[2024:Music Audio Generation]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2024:Music Description & Captioning]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang]>
* [[2024:Polyphonic Transcription]] <TC: [mailto:yujia.yan@rochester.edu Yujia Yan] & [mailto:ziyu.wang@nyu.edu Ziyu Wang]>
* [[2024:Singing Voice Deepfake Detection]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang] & [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang]>
* [[2024:Cover Song Identification]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2024:Lyrics-to-Audio Alignment]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2021:Audio Beat Tracking]]
* [[2021:Audio Chord Estimation]]
* [[2021:Audio Cover Song Identification]]
* [[2021:Audio Downbeat Estimation]]
* [[2021:Audio Fingerprinting]]
* [[2021:Audio Key Detection]]
* [[2021:Audio Melody Extraction]]
* [[2021:Audio Onset Detection]]
* [[2021:Audio Tag Classification]]
* [[2021:Audio Tempo Estimation]]
* [[2021:Automatic Lyrics Transcription]]
* [[2021:Drum Transcription]]
* [[2021:Multiple Fundamental Frequency Estimation & Tracking]]
* [[2021:Music Detection]]
* [[2021:Patterns for Prediction]] (offshoot of [[2017:Discovery of Repeated Themes & Sections]])
* [[2021:Query by Singing/Humming]]
* [[2021:Query by Tapping]]
* [[2021:Real-time Audio to Score Alignment (a.k.a Score Following)]]
* [[2021:Set List Identification]]
* [[2021:Structural Segmentation]]
* [[2020:Singing_Transcription_from_Polyphonic_Music]]
* [[2018:Music and/or Speech Detection]]
* [[2016:GC16UX|2016:Grand Challenge on User Experience]]
* [[2016:Audio Offset Detection]]

2026:Call for Challenges

2026-03-16T04:45:52Z

Junyan: /* Call for Challenge Proposals & Task Captains */

==Call for Challenge Proposals & Task Captains==

We invite the ISMIR community to participate in shaping the future of Music Information Retrieval (MIR) by either '''proposing new research challenges''' or '''volunteering as task captains for [https://www.music-ir.org/mirex/wiki/2025:Previous_Tasks existing ones]'''.

* New challenge proposals should aim to address cutting-edge problems and push the boundaries of current MIR research.
* Task captains for established tasks are encouraged to help revitalize them—potentially by updating evaluation methodologies, datasets, or other aspects to reflect recent advances in the field.

We also welcome challenge sponsors from both industry and academia, particularly those willing to contribute datasets, evaluation tools, or computational resources to support the competition. This may include proprietary test sets, i.e., datasets that remain private and are not disclosed to participants or MIREX organizers.

What's new:

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

For all tasks, task submissions are encouraged to report key resource indicators, including:

training data size
model size
other computational resources used in model development
Task captains are encouraged to summarize and report this information in the task results page.

Rules
For both new and established tasks, all proposals must have an assigned task captain responsible for evaluating participant submissions.

Task Captain Responsibilities:

Register on the MIREX Wiki and maintain the task description page.
Collect submissions via the MIREX submission server (or provide customized submission instructions).
Execute and evaluate the submissions.
Report results to MIREX and create a results page on the MIREX Wiki.
(Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.
Submission Format
A call for challenge proposal must contain the following content:

Title of the new task
Abstract
Task description
Significance of the task
Evaluation criteria
Datasets and resources provided
Requirements for submission
Task captain information (name, title, affiliation, email, and MIREX Wiki username)
Long-term plan (your willingness and availability to maintain the task in coming years)

A task captain proposal should contain the following content:

Title of the existing task
Abstract
Task description
Evaluation criteria, if different from previous MIREXes
Datasets and resources provided, if different from previous MIREXes
Requirements for submission, if different from previous MIREXes
Task captain information (name, title, affiliation, email, and MIREX Wiki username)
Long-term plan (your willingness and availability to maintain the task in coming years)
Please submit a 1-4 page PDF to the MIREX organizing committee future-mirex@googlegroups.com before the due date.

Multiple submissions
A single individual may serve as the task captain for multiple tasks.
Conversely, a single task may be co-managed by multiple task captains.
If we receive similar proposals from different authors, we may reach out to coordinate a joint effort to co-host the task.
Deadlines
Challenge proposals due: May 22, 2026
Notification of acceptance: May 29, 2026
Contact Us
We look forward to receiving your innovative and impactful challenge proposals. If you have any questions, please do not hesitate to contact the MIREX organizing committee future-mirex@googlegroups.com.

MIREX 2026 Organizers:

Gus Xia, MBZUAI
Junyan Jiang, New York University
Akira Maezawa, Yamaha
Ziyu Wang, New York University
Yixiao Zhang, ByteDance
Ruibin Yuan, Hong Kong University of Science and Technology
J. Stephen Downie, University of Illinois
We also welcome challenge ''sponsors'' from both industry and academia, particularly those willing to contribute datasets, evaluation tools, or computational resources to support the competition. This may include proprietary test sets, i.e., datasets that remain private and are not disclosed to participants or MIREX organizers.

'''What's new:'''

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

For all tasks, task submissions are encouraged to report key resource indicators, including:

* training data size
* model size
* other computational resources used in model development

Task captains are encouraged to summarize and report this information in the task results page.

==Rules==

For both new and established tasks, all proposals must have an assigned task captain responsible for evaluating participant submissions.

'''Task Captain Responsibilities:'''
* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain the task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

==Submission Format==

A call for challenge proposal must contain the following content:

# Title of the new task
# Abstract
# Task description
# Significance of the task
# Evaluation criteria
# Datasets and resources provided
# Requirements for submission
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

A task captain proposal should contain the following content:

# Title of the existing task
# Abstract
# Task description
# Evaluation criteria, if different from previous MIREXes
# Datasets and resources provided, if different from previous MIREXes
# Requirements for submission, if different from previous MIREXes
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

Please submit a 1-4 page PDF to the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com] before the due date.

===Multiple submissions===
* A single individual may serve as the task captain for multiple tasks.
* Conversely, a single task may be co-managed by multiple task captains.
* If we receive similar proposals from different authors, we may reach out to coordinate a joint effort to co-host the task.

==Deadlines==

* Challenge proposals due: May 22, 2026
* Notification of acceptance: May 29, 2026

==Contact Us==

We look forward to receiving your innovative and impactful challenge proposals. If you have any questions, please do not hesitate to contact the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

MIREX 2026 Organizers:
* Gus Xia, MBZUAI
* Junyan Jiang, New York University
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2026:Call for Challenges

2026-03-16T04:43:40Z

Junyan:

==Call for Challenge Proposals & Task Captains==

We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge ''sponsors'' from both industry and academia, particularly those willing to contribute datasets, evaluation tools, or computational resources to support the competition. This may include proprietary test sets, i.e., datasets that remain private and are not disclosed to participants or MIREX organizers.

'''What's new:'''

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

For all tasks, task submissions are encouraged to report key resource indicators, including:

* training data size
* model size
* other computational resources used in model development

Task captains are encouraged to summarize and report this information in the task results page.

==Rules==

For both new and established tasks, all proposals must have an assigned task captain responsible for evaluating participant submissions.

'''Task Captain Responsibilities:'''
* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain the task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

==Submission Format==

A call for challenge proposal must contain the following content:

# Title of the new task
# Abstract
# Task description
# Significance of the task
# Evaluation criteria
# Datasets and resources provided
# Requirements for submission
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

A task captain proposal should contain the following content:

# Title of the existing task
# Abstract
# Task description
# Evaluation criteria, if different from previous MIREXes
# Datasets and resources provided, if different from previous MIREXes
# Requirements for submission, if different from previous MIREXes
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

Please submit a 1-4 page PDF to the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com] before the due date.

===Multiple submissions===
* A single individual may serve as the task captain for multiple tasks.
* Conversely, a single task may be co-managed by multiple task captains.
* If we receive similar proposals from different authors, we may reach out to coordinate a joint effort to co-host the task.

==Deadlines==

* Challenge proposals due: May 22, 2026
* Notification of acceptance: May 29, 2026

==Contact Us==

We look forward to receiving your innovative and impactful challenge proposals. If you have any questions, please do not hesitate to contact the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

MIREX 2026 Organizers:
* Gus Xia, MBZUAI
* Junyan Jiang, New York University
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2026:Call for Challenges

2026-03-16T04:38:48Z

Junyan: Created page with "==Call for Challenge Proposals & Task Captains== We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retr..."

==Call for Challenge Proposals & Task Captains==

We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge ''sponsors'' from both industry and academia, particularly those willing to contribute datasets, evaluation tools, or computational resources to support the competition. This includes proprietary test sets—that is, datasets which will remain private and not be disclosed to either participants or MIREX organizers.

'''What's new:'''

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

Furthermore, all task captains are encouraged to report key resource indicators for each submission, including:

* training data size
* model size
* other computational resources used in model development

==Rules==

For both new and established tasks, all proposals must have an assigned task captain responsible for evaluating participant submissions.

'''Task Captain Responsibilities:'''
* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain the task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

==Submission Format==

A call for challenge proposal must contain the following content:

# Title of the new task
# Abstract
# Task description
# Significance of the task
# Evaluation criteria
# Datasets and resources provided
# Requirements for submission
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

A task captain proposal should contain the following content:

# Title of the existing task
# Abstract
# Task description
# Evaluation criteria, if different from previous MIREXes
# Datasets and resources provided, if different from previous MIREXes
# Requirements for submission, if different from previous MIREXes
# Task captain information (name, title, affiliation, email, and MIREX Wiki username)
# Long-term plan (your willingness and availability to maintain the task in coming years)

Please submit a 1-4 page PDF to the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com] before the due date.

===Multiple submissions===
* A single individual may serve as the task captain for multiple tasks.
* Conversely, a single task may be co-managed by multiple task captains.
* If we receive similar proposals from different authors, we may reach out to coordinate a joint effort to co-host the task.

==Deadlines==

* Challenge proposals due: May 22, 2026
* Notification of acceptance: May 29, 2026

==Contact Us==

We look forward to receiving your innovative and impactful challenge proposals. If you have any questions, please do not hesitate to contact the MIREX organizing committee [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

MIREX 2026 Organizers:
* Gus Xia, MBZUAI
* Junyan Jiang, New York University
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

MIREX HOME

2026-03-16T04:35:57Z

Junyan: /* Call for Challenges */

==Welcome to MIREX 2026==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2026.ismir.net/ Abu Dhabi, UAE] from November 8-12, 2026, possibly with an online component.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Call for Challenges==

We invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field. We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2026:Call for Challenges]].

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

===What's new:===

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

Furthermore, all task captains are encouraged to report key resource indicators for each submission, including:

* training data size
* model size
* other computational resources used in model development

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2026.

==Important Dates==

* Challenge proposals due: May 22, 2026
* Notification of acceptance: May 29, 2026
* Submission open: Jul 1, 2026
* Submission close: Oct 1, 2026 (Some tasks may have a different deadline; see task descriptions)
* Result published: Oct 15, 2026 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source evaluation pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2026!

Future MIREX Team, 2026

MIREX 2026 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

MIREX HOME

2026-03-16T04:33:51Z

Junyan:

==Welcome to MIREX 2026==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2026.ismir.net/ Abu Dhabi, UAE] from November 8-12, 2026, possibly with an online component.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Call for Challenges==

Starting with 2024, we invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2026:Call for Challenges]].

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2026.

===What's new:===

In MIREX 2026, we introduce two special calls for challenges:

1. Novel evaluation pipelines

There is a growing need for new evaluation methodologies. We welcome challenge proposals that introduce novel evaluation pipelines, including but not limited to the evaluation of generative models, interactive systems, and other emerging paradigms.

2. Evaluation under limited resources

In addition to state-of-the-art systems, MIREX aims to better support researchers and research areas with limited resources. We welcome challenge proposals that focus on underrepresented research areas, music genres, or research communities.

Furthermore, all task captains are encouraged to report key resource indicators for each submission, including:

* training data size
* model size
* other computational resources used in model development

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2026.

==Important Dates==

* Challenge proposals due: May 22, 2026
* Notification of acceptance: May 29, 2026
* Submission open: Jul 1, 2026
* Submission close: Oct 1, 2026 (Some tasks may have a different deadline; see task descriptions)
* Result published: Oct 15, 2026 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source evaluation pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2026!

Future MIREX Team, 2026

MIREX 2026 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2025:Main Page

2026-03-16T04:04:38Z

Junyan:

==Welcome to MIREX 2025==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2025.ismir.net/ Daejeon, South Korea] from September 21-25, 2025.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Task Descriptions==

Traditional MIR tasks
* [[2025:Audio Chord Estimation]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

==Call for Challenges==

Starting with MIREX 2025, we invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2025:Call for Challenges]].

===What's new:===

Starting with MIREX 2025, we invite the ISMIR community to participate in shaping the future of Music Information Retrieval (MIR) by either '''proposing new research challenges''' or '''volunteering as task captains''' for existing ones.

* '''New challenge proposals''' should aim to address cutting-edge problems and push the boundaries of current MIR research.
* '''Task captains for established tasks''' are encouraged to help revitalize previous tasks—potentially by updating evaluation methodologies, datasets, or other aspects to reflect recent advances in the field.

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2025.

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2025.

==Important Dates==

* <del>Challenge proposals due: May 9, 2025</del>
* <del>Notification of acceptance: May 16, 2025</del>
* Submission open: May 31, 2025
* Submission close: Sept 1, 2025 (Some tasks may have a different deadline; see task descriptions)
* Result published: Sept 12, 2025 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source evaluation pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2025!

Future MIREX Team, 2025

MIREX 2025 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

MediaWiki:Sidebar

2026-03-16T04:04:08Z

Junyan:

MediaWiki:Sidebar

2026-03-16T04:03:57Z

Junyan:

MIREX HOME

2026-02-02T14:47:22Z

Junyan: /* Contact Us */

MIREX HOME

2026-02-02T14:47:06Z

Junyan: /* Contact Us */

==Welcome to MIREX 2025==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2025.ismir.net/ Daejeon, South Korea] from September 21-25, 2025.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Task Descriptions==

Traditional MIR tasks
* [[2025:Audio Chord Estimation]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

==Call for Challenges==

Starting with MIREX 2025, we invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2025:Call for Challenges]].

===What's new:===

Starting with MIREX 2025, we invite the ISMIR community to participate in shaping the future of Music Information Retrieval (MIR) by either '''proposing new research challenges''' or '''volunteering as task captains''' for existing ones.

* '''New challenge proposals''' should aim to address cutting-edge problems and push the boundaries of current MIR research.
* '''Task captains for established tasks''' are encouraged to help revitalize previous tasks—potentially by updating evaluation methodologies, datasets, or other aspects to reflect recent advances in the field.

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2025.

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2025.

==Important Dates==

* <del>Challenge proposals due: May 9, 2025</del>
* <del>Notification of acceptance: May 16, 2025</del>
* Submission open: May 31, 2025
* Submission close: Sept 1, 2025 (Some tasks may have a different deadline; see task descriptions)
* Result published: Sept 12, 2025 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====Repositories====

Open-source Evaluation Pipelines: https://github.com/ismir-mirex/mirex-evaluation

Github Organization: https://github.com/ismir-mirex/

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2025!

Future MIREX Team, 2025

MIREX 2025 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2025:Main Page

2025-11-10T09:02:43Z

Junyan: Created page with "==Welcome to MIREX 2025== After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want..."

==Welcome to MIREX 2025==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2025.ismir.net/ Daejeon, South Korea] from September 21-25, 2025.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Task Descriptions==

Traditional MIR tasks
* [[2025:Audio Chord Estimation]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

==Call for Challenges==

Starting with MIREX 2025, we invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2025:Call for Challenges]].

===What's new:===

Starting with MIREX 2025, we invite the ISMIR community to participate in shaping the future of Music Information Retrieval (MIR) by either '''proposing new research challenges''' or '''volunteering as task captains''' for existing ones.

* '''New challenge proposals''' should aim to address cutting-edge problems and push the boundaries of current MIR research.
* '''Task captains for established tasks''' are encouraged to help revitalize previous tasks—potentially by updating evaluation methodologies, datasets, or other aspects to reflect recent advances in the field.

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2025.

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2025.

==Important Dates==

* <del>Challenge proposals due: May 9, 2025</del>
* <del>Notification of acceptance: May 16, 2025</del>
* Submission open: May 31, 2025
* Submission close: Sept 1, 2025 (Some tasks may have a different deadline; see task descriptions)
* Result published: Sept 12, 2025 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2025!

Future MIREX Team, 2025

MIREX 2025 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

MIREX HOME

2025-11-10T05:55:19Z

Junyan: /* LinkedIn Organization Page */

==Welcome to MIREX 2025==

After a break of 3 years, we want to bring back the MIREX (Music Information Retrieval Evaluation eXchange) competition starting from 2024. We want to bring in new tasks, benchmarks, and datasets in response to the rapid development of computer music research.

The MIREX community will hold its annual meeting as part of [https://ismir.net/ The International Society for Music Information Retrieval Conference]. This year, the conference will be held in [https://ismir2025.ismir.net/ Daejeon, South Korea] from September 21-25, 2025.

In a long run, we want to make MIREX a platform for researchers to share their latest research results, to compare their systems with others, and to promote the development of the field.

==Task Descriptions==

Traditional MIR tasks
* [[2025:Audio Chord Estimation]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

==Call for Challenges==

Starting with MIREX 2025, we invite the ISMIR community to propose new research challenges that address cutting-edge problems in Music Information Retrieval (MIR). These challenges should aim to push the boundaries of current research and foster innovation in the field.

We also welcome challenge sponsors from both industry and research institutions, particularly those willing to contribute datasets and computational resources to support the competition.

For the format and requirements for the challenge proposal, please go to [[2025:Call for Challenges]].

===What's new:===

Starting with MIREX 2025, we invite the ISMIR community to participate in shaping the future of Music Information Retrieval (MIR) by either '''proposing new research challenges''' or '''volunteering as task captains''' for existing ones.

* '''New challenge proposals''' should aim to address cutting-edge problems and push the boundaries of current MIR research.
* '''Task captains for established tasks''' are encouraged to help revitalize previous tasks—potentially by updating evaluation methodologies, datasets, or other aspects to reflect recent advances in the field.

Task Captain Responsibilities:

* Register on the [https://www.music-ir.org/mirex MIREX Wiki] and maintain a task description page.
* Collect submissions via the MIREX submission server (or provide customized submission instructions).
* Execute and evaluate the submissions.
* Report results to MIREX and create a results page on the MIREX Wiki.
* (Optional) Present a MIREX task captain poster at the Late-Breaking and Demo (LBD) session at ISMIR 2025.

==How to Participate==

See also the general [[Submission Guidelines]].

* Read the [[Participant Agreement]] and task description carefully.
* Program your system.
* Write a 2-4 page extended abstract PDF describing your system.
* Submit your system and extended abstract to the [http://futuremirex.com/submission MIREX submission site].
* Top-performing teams will have the opportunity to present their MIREX posters at the LBD session at ISMIR 2025.

==Important Dates==

* <del>Challenge proposals due: May 9, 2025</del>
* <del>Notification of acceptance: May 16, 2025</del>
* Submission open: May 31, 2025
* Submission close: Sept 1, 2025 (Some tasks may have a different deadline; see task descriptions)
* Result published: Sept 12, 2025 (Some tasks may have a different deadline; see task descriptions)

==Contact Us==

====Email====

For general questions, feedback, and suggestions, please send messages to our mailing list [mailto:future-mirex@googlegroups.com future-mirex@googlegroups.com].

For task-specific questions, we have listed the email for each task captain [[MIREX_HOME#Task_Descriptions|here]].

====Discord Server====

For real-time discussion with the MIREX organizers or task captains, you may join our [https://discord.gg/vC2YWX29sC discord server].

Notice: some task captains are not in the discord server.

====LinkedIn Organization Page====

You may visit our LinkedIn organization page [https://www.linkedin.com/company/future-mirex/ here].

We are looking forward to seeing you at MIREX 2025!

Future MIREX Team, 2025

MIREX 2025 Organizers:
* Junyan Jiang, New York University
* Gus Xia, MBZUAI
* Akira Maezawa, Yamaha
* Ziyu Wang, New York University
* Yixiao Zhang, ByteDance Inc.
* Ruibin Yuan, Hong Kong University of Science and Technology
* J. Stephen Downie, University of Illinois

2025:Music Structure Analysis Results

2025-09-19T14:31:01Z

Junyan: /* Results */

=Results=

{| class="wikitable" style="vertical-align:bottom;"
|- style="font-weight:bold;"
! System
! Methods Used
! Trained on the training set of
! style="text-align:right;" | ACC
! style="text-align:right;" | HR.5
! style="text-align:right;" | HR3
! PDF
|-
| Baseline 1
| MusicFM
| Harmonix Set
| style="text-align:right;" | 0.705
| style="text-align:right;" | '''0.644'''
| style="text-align:right;" | 0.710
|
|-
| kgstruct
| All-in-One variance
| External data (6k songs)
| style="text-align:right;" | '''0.720'''
| style="text-align:right;" | 0.590
| style="text-align:right;" | '''0.762'''
| [http://futuremirex.com/portal/wp-content/uploads/2025/music-structure-analysis/kgstruct.pdf PDF]
|}

* Reported by paper results.

2025:RenCon Results

2025-09-19T14:29:41Z

Junyan: /* System Rankings */

= 2025:RenCon Results =

== Preliminary (Audition) Round Results ==

=== Evaluation Methodology ===
The preliminary round was evaluated through an online listening test with '''25 expert evaluators'''. The evaluation used a weighted voting system where participants self-rated their expertise level from 1-5 stars, with responses weighted accordingly.

=== Participant Demographics ===
Our evaluation panel consisted of highly qualified judges:

'''Expertise Distribution:'''
* Expert evaluators (5 stars): 7 participants (29.2%)
* High confidence (4 stars): 5 participants (20.8%)
* Moderate confidence (3 stars): 10 participants (41.7%)
* Lower confidence (1-2 stars): 2 participants (8.4%)
* '''Average expertise weight:''' 3.67/5.0

'''Professional Background:'''
* Music researchers: 12 (54.5%)
* Music technologists: 10 (45.5%)
* Active performers: 8 (36.4%)
* Conservatory students: 6 (27.3%)
* Music lovers: 15 (68.2%)
* Concert-goers: 8 (36.4%)

'''Musical Experience:'''
* Strong representation of classical music expertise
* Diverse musical preferences spanning classical, jazz, pop, and rock
* Substantial piano experience among evaluators
* Mix of academic researchers and practicing musicians

=== System Rankings ===

The following table shows the final rankings based on weighted average scores from the preliminary round evaluation:
{| class="wikitable sortable"
! Rank
! Anonymous Name
! Real System Name
! Authors/Institution
! Weighted Score
! PDF
|-
| 1
| MidnightOpal
| DirectorMusices
| Anders Friberg, Gabriel Jones
| 4.33/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/DirectorMusices.pdf PDF]
|-
| 2
| CrystalEcho
| VirtuosoNet
| Dasaem Jeong, Taegyun Kwon, Yoojin Kim, Kyogu Lee, Juhan Nam
| 3.54/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/VirtuosoNet.pdf PDF]
|-
| 3
| FrozenRiver
| Midihum
| Erich Grunewald
| 3.32/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/Midihum.pdf PDF]
|-
| 4
| VelvetStorm
| ElegantAIPianist
| Leduo Chen, Xinrui Su, Yuqiang Li, Honyu Andy Shing, Junchuan Zhao, Zihan Chai, Kunyang Zhang, Shengchen Li
| 3.19/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/ElegantAIPianist.pdf PDF]
|-
| 5
| SilverWave
| Contin-U
| Jongmin Jung, Dongmin Kim, Sihun Lee, Seola Cho, Hyungjoon Soh, Irmak Bukey, Chris Donahue, Dasaem Jeong
| 3.00/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/Contin-U.pdf PDF]
|-
| 6
| EmberSky
| YQX+
| Jinwen Zhou, Yuncong Xie, Haochen Wang, Huan Zhang, Aidan Hogg, Simon Dixon
| 2.83/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/YQX+.pdf PDF]
|-
|
| CrimsonDawn
| ScorePerLockNAR
| Weixi Zhai
| 2.53/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/ScorePerLockNAR.pdf PDF]
|-
|
| AzureThunder
| RenConnoisseur
| Silvan Peter
| 2.53/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/RenConnoisseur.pdf PDF]
|-
|
| GoldenMist
| CueFreeExpressPedal
| Kyle Worrall, Tom Collins
| 2.31/5.0
| [https://futuremirex.com/portal/wp-content/uploads/2025/rencon/CueFreeExpressPedal.pdf PDF]
|}

''Note: Complete rankings and system details will be updated following the live contest and final results announcement.''

=== Qualitative Feedback ===

Evaluators provided extensive qualitative feedback on the systems' performances:

'''Common Positive Attributes:'''
* Natural expressiveness and human-like phrasing
* Appropriate tempo variations and rubato
* Musical sensitivity to harmonic structure
* Dynamic expression and articulation

'''Areas for Improvement:'''
* Consistency across different musical styles
* Handling of complex rhythmic patterns
* Balance between technical accuracy and musical expression

== Live Contest Results ==

''[To be updated following the live contest on September 25, 2025]''

=== Surprise Piece ===
* '''Title:''' [To be announced]
* '''Composer:''' [To be announced]
* '''Duration:''' [X minutes]
* '''Style:''' [Musical characteristics]

=== Live Performance Rankings ===
''[Results pending live audience voting]''

=== Winner Announcement ===
''[To be announced at the conclusion of ISMIR 2025]''

== External Links ==

* [https://ren-con2025.vercel.app/ Official RenCon 2025 Website]
* [https://ismir2025.ismir.net/ ISMIR 2025 Conference Website]
* [https://www.music-ir.org/mirex/wiki/2025:RenCon RenCon 2025 MIREX Task Page]

[[Category:MIREX]]
[[Category:ISMIR 2025]]
[[Category:Performance Rendering]]
[[Category:Competition Results]]

2025:Symbolic Music Generation Results

2025-09-19T14:23:33Z

Junyan: /* Submissions */

= Submissions =

{| class="wikitable"
|- style="font-weight:bold;"
! Team
! Extended Abstract
! Methods
|-
| RWKV (Zhou-Zheng et al.)
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/RWKV.pdf PDF]
| RWKV
|-
| PixelGen
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/PixelGen.pdf PDF]
| Hierarchical Transformer
|-
| MuseCoco (BL-1)
| [https://arxiv.org/abs/2306.00110]
| Transformer
|-
| Anticipatory Music Transformer (BL-2)
| [https://arxiv.org/abs/2306.08620]
| Transformer
|-
|}

=Results=

{| class="wikitable" style="text-align:center;"
|- style="font-weight:bold; vertical-align:center;"
! rowspan="2" | Team
! colspan="4" | Subjective Evaluation
|- style="font-weight:bold; vertical-align:center;"
| Coherecy ↑
| Structure ↑
| Creativity ↑
| Musicality ↑
|-
| RWKV (Zhou-Zheng et al.)
| 3.57 ± 0.10a
| 3.58 ± 0.10a
| 3.26 ± 0.10a
| '''3.50 ± 0.10a'''
|-
| PixelGen
| 2.39 ± 0.10c
| 2.37 ± 0.09c
| 2.85 ± 0.09b
| 2.48 ± 0.09c
|-
| MuseCoco (BL-1)
| 3.11 ± 0.10b
| 3.07 ± 0.09b
| 3.08 ± 0.09ab
| 2.95 ± 0.09b
|-
| Anticipatory Music Transformer (BL-2)
| '''3.70 ± 0.10a'''
| '''3.69 ± 0.09a'''
| '''3.30 ± 0.10a'''
| 3.45 ± 0.10a
|}

'''Evaluation Results'''

Results are reported in the form of mean ± sems (sem refers to standard error of mean), where s is a letter. Different letters within a column indicate significant differences (p-value p < 0.05) based on a Wilcoxon signed rank test with Holm-Bonferroni correction.

'''Baseline Models'''

For MuseCoco, we use the ''xlarge'' model with 1.2 billion learnable parameters. For Anticipatory Music Transformer, we use the ''Large'' model with 780M learnable parameters.

'''Subjective Evaluation Details'''

A double-blind online survey was conducted to test music quality. Each model was anonymised, and for each test prompt, a sample was cherry-picked from 8 generated candidates. A total of 8 prompts of varied styles (pop, classical, and jazzy) were tested, resulting in an 8-page survey. The page order and the sample order within each page were both randomised.

Responses were collected from 20 participants with diverse music backgrounds. 14 participants completed all 8 pages with an average completion time of 32 minutes.

2025:Symbolic Music Generation Results

2025-09-19T14:23:14Z

Junyan: /* Submissions */

= Submissions =

{| class="wikitable"
|- style="font-weight:bold;"
! Team
! Extended Abstract
! Methods
|-
| RWKV (Zhou-Zheng et al.)
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/RWKV.pdf PDF]
| RWKV
|-
| PixelGen
| [http://futuremirex.com/portal/wp-content/uploads/2025/symbolic-music-generation/PuxelGen.pdf PDF]
| Hierarchical Transformer
|-
| MuseCoco (BL-1)
| [https://arxiv.org/abs/2306.00110]
| Transformer
|-
| Anticipatory Music Transformer (BL-2)
| [https://arxiv.org/abs/2306.08620]
| Transformer
|-
|}

=Results=

{| class="wikitable" style="text-align:center;"
|- style="font-weight:bold; vertical-align:center;"
! rowspan="2" | Team
! colspan="4" | Subjective Evaluation
|- style="font-weight:bold; vertical-align:center;"
| Coherecy ↑
| Structure ↑
| Creativity ↑
| Musicality ↑
|-
| RWKV (Zhou-Zheng et al.)
| 3.57 ± 0.10a
| 3.58 ± 0.10a
| 3.26 ± 0.10a
| '''3.50 ± 0.10a'''
|-
| PixelGen
| 2.39 ± 0.10c
| 2.37 ± 0.09c
| 2.85 ± 0.09b
| 2.48 ± 0.09c
|-
| MuseCoco (BL-1)
| 3.11 ± 0.10b
| 3.07 ± 0.09b
| 3.08 ± 0.09ab
| 2.95 ± 0.09b
|-
| Anticipatory Music Transformer (BL-2)
| '''3.70 ± 0.10a'''
| '''3.69 ± 0.09a'''
| '''3.30 ± 0.10a'''
| 3.45 ± 0.10a
|}

'''Evaluation Results'''

Results are reported in the form of mean ± sems (sem refers to standard error of mean), where s is a letter. Different letters within a column indicate significant differences (p-value p < 0.05) based on a Wilcoxon signed rank test with Holm-Bonferroni correction.

'''Baseline Models'''

For MuseCoco, we use the ''xlarge'' model with 1.2 billion learnable parameters. For Anticipatory Music Transformer, we use the ''Large'' model with 780M learnable parameters.

'''Subjective Evaluation Details'''

A double-blind online survey was conducted to test music quality. Each model was anonymised, and for each test prompt, a sample was cherry-picked from 8 generated candidates. A total of 8 prompts of varied styles (pop, classical, and jazzy) were tested, resulting in an 8-page survey. The page order and the sample order within each page were both randomised.

Responses were collected from 20 participants with diverse music backgrounds. 14 participants completed all 8 pages with an average completion time of 32 minutes.

2025:Audio Beat Tracking Results

2025-09-19T14:20:06Z

Junyan: /* Submissions */

== Submissions ==

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-beat-tracking/KG-ApolloBeats.pdf PDF]
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG-ApolloBeats 2
| The 2025 KG Music Beats Tracking System
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-beat-tracking/KG-ApolloBeats.pdf PDF]
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-beat-tracking/BeatU.pdf PDF]
| Jingwei Zhao, Rei Nishiyama, Kouhei Sumi, Takuya Fujishima, Akira Maezawa
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 92.98
| 82.75
| 91.63
| 93.66
| 85.79
| 90.57
| 88.27
| 93.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 95.87
| 87.43
| 95.20
| 95.29
| 88.53
| 92.00
| 90.72
| 94.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Music Structure Analysis Results

2025-09-19T14:16:50Z

Junyan: /* Results */

=Results=

{| class="wikitable" style="vertical-align:bottom;"
|- style="font-weight:bold;"
! System
! Methods Used
! Trained on the training set of
! style="text-align:right;" | ACC
! style="text-align:right;" | HR.5
! style="text-align:right;" | HR3
|-
| Baseline 1
| MusicFM
| Harmonix Set
| style="text-align:right;" | 0.705
| style="text-align:right;" | '''0.644'''
| style="text-align:right;" | 0.710
|-
| kgstruct [http://futuremirex.com/portal/wp-content/uploads/2025/music-structure-analysis/kgstruct.pdf PDF]
| All-in-One variance
| External data (6k songs)
| style="text-align:right;" | '''0.720'''
| style="text-align:right;" | 0.590
| style="text-align:right;" | '''0.762'''
|}

* Reported by paper results.

2025:Music Structure Analysis Results

2025-09-19T14:15:58Z

Junyan: /* Results */

=Results=

{| class="wikitable" style="vertical-align:bottom;"
|- style="font-weight:bold;"
! System
! Methods Used
! Trained on the training set of
! style="text-align:right;" | ACC
! style="text-align:right;" | HR.5
! style="text-align:right;" | HR3
|-
| Baseline 1
| MusicFM
| Harmonix Set
| style="text-align:right;" | 0.705
| style="text-align:right;" | '''0.644'''
| style="text-align:right;" | 0.710
|-
| [http://futuremirex.com/portal/wp-content/uploads/2025/kgstruct.pdf kgstruct]
| All-in-One variance
| External data (6k songs)
| style="text-align:right;" | '''0.720'''
| style="text-align:right;" | 0.590
| style="text-align:right;" | '''0.762'''
|}

* Reported by paper results.

2025:Cover Song Identification Results

2025-09-19T14:13:28Z

Junyan: /* Submissions */

== Submissions ==

{| class="wikitable" style="text-align:right; vertical-align:bottom;"
|- style="font-weight:bold; text-align:left;"
! Team
! Methods
! mAP
! Rank-1
! Rank-5
! Rank-10
! PDF
|-
| style="text-align:left;" | Tencent
| style="text-align:left;" | MuCrossCover3
| 0.958
| 0.974
| 0.984
| 0.986
| style="text-align:left;" | [http://futuremirex.com/portal/wp-content/uploads/2025/cover-song-identification/MuCrossCover3.pdf PDF]
|}

== Revisions ==

TBD (Potential Data Issue)

2025:Audio Chord Estimation Results

2025-09-19T14:10:42Z

Junyan:

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| Baseline: ISMIR2019
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| MD1
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-chord-estimation/MD1.pdf PDF]
| Masayuki Doai
|-
| wu-ensemble
| wu-ensemble
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-chord-estimation/wu-ensemble.pdf PDF]
| Yiwei Ding, Christof Weiß
|-
| wu-single
| wu-single
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-chord-estimation/wu-single.pdf PDF]
| Yiwei Ding, Christof Weiß
|-
| YK1
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-chord-estimation/YK1.pdf PDF]
| Yiming Wu, Kento Yoshida
|-
| BMACE
| A Mamba-Based Model for Automatic Chord Recognition
| [http://futuremirex.com/portal/wp-content/uploads/2025/audio-chord-estimation/BMACE.pdf PDF]
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
|}

= Test Sets =

====Main Test Sets====

The following datasets are served as pure test sets. No system is allowed to train on them.

* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

====Additional Test Sets====

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

= Main Results =

The following datasets are served as pure test sets. No system is allowed to train on them.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 55.72
| 8.88
| 8.70
| 2.52
| 2.45
| 68.16
| 90.86
| 56.60
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.35
| 79.15
| 77.91
| 66.40
| 65.33
| 86.17
| 85.50
| 88.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 81.01
| 78.10
| 75.41
| 64.53
| 62.05
| 85.50
| 85.08
| 87.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 74.64
| 71.97
| 70.72
| 55.06
| 53.96
| 83.19
| 86.29
| 82.20
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 75.77
| 73.14
| 71.74
| 55.41
| 54.15
| 83.16
| 85.44
| 83.08
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 71.06
| 67.18
| 65.09
| 48.88
| 47.06
| 81.60
| 83.14
| 82.71
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 78.61
| 76.39
| 74.72
| 64.15
| 62.65
| 83.39
| 78.57
| 92.78
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 58.92
| 12.59
| 12.29
| 4.52
| 4.34
| 71.62
| 91.05
| 60.47
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.83
| 80.22
| 78.87
| 64.13
| 63.14
| 88.09
| 88.67
| 88.47
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 82.53
| 79.71
| 75.60
| 66.02
| 62.31
| 88.94
| 89.78
| 89.33
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 82.54
| 81.29
| 78.99
| 62.84
| 60.84
| 87.48
| 88.68
| 87.43
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 81.37
| 79.69
| 77.61
| 61.60
| 59.84
| 87.03
| 89.81
| 85.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 77.57
| 74.64
| 71.59
| 56.38
| 53.90
| 86.51
| 87.25
| 87.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 82.00
| 81.16
| 79.69
| 66.97
| 65.77
| 89.04
| 86.43
| 93.49
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 52.38
| 11.90
| 11.65
| 2.37
| 2.23
| 71.98
| 90.23
| 60.42
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 79.34
| 77.10
| 76.07
| 55.59
| 54.71
| 88.00
| 88.13
| 88.20
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 80.13
| 77.03
| 72.85
| 61.24
| 57.26
| 89.42
| 89.71
| 89.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 79.58
| 77.58
| 75.57
| 54.36
| 52.58
| 87.22
| 88.44
| 86.55
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 78.87
| 76.56
| 74.66
| 55.35
| 53.60
| 87.19
| 89.30
| 85.70
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.49
| 71.99
| 69.24
| 52.40
| 49.97
| 86.66
| 85.89
| 88.28
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 81.49
| 79.99
| 78.58
| 62.81
| 61.61
| 90.09
| 87.21
| 93.88
|}

= Additional Results =

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.
== Billboard2012 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 58.45
| 9.13
| 9.00
| 2.91
| 2.86
| 69.55
| 92.02
| 57.41
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 85.11
| 83.98
| 82.76
| 74.12
| 73.12
| 88.80
| 88.63
| 89.78
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 85.90
| 84.66
| 81.81
| 77.22
| 74.45
| 88.43
| 87.88
| 89.58
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 78.26
| 77.15
| 75.58
| 59.99
| 58.79
| 84.42
| 87.98
| 82.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 79.23
| 78.21
| 76.76
| 60.23
| 59.07
| 84.87
| 87.19
| 84.24
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 83.69
| 85.33
| 83.48
|}

== RWC-Popular ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 56.48
| 11.97
| 11.78
| 2.41
| 2.30
| 72.59
| 90.92
| 61.06
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 83.98
| 81.18
| 79.42
| 66.53
| 64.83
| 88.53
| 88.53
| 88.84
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 88.76
| 87.27
| 81.14
| 76.88
| 70.90
| 91.90
| 91.55
| 92.43
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 81.87
| 80.30
| 77.58
| 62.65
| 60.25
| 87.51
| 89.95
| 85.65
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 82.48
| 81.35
| 78.48
| 62.86
| 60.28
| 87.81
| 89.47
| 86.64
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 78.97
| 77.78
| 74.13
| 63.15
| 59.72
| 88.64
| 88.07
| 89.76
|}

= Task Captain's Note =

* Results on Billboard & RWC Popular are competible with previous years.
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results

2025:MIREX2025 Results

2025-09-19T14:07:19Z

Junyan:

==Overall Results Poster==

[http://futuremirex.com/portal/wp-content/uploads/2025/MIREX%20Poster.pdf MIREX 2025 Results Poster (PDF)]

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

====Online Poster====
The deadline of submitting an online poster is Oct 7th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:MIREX2025 Results

2025-09-19T14:06:17Z

Junyan:

==Overall Results Poster==

[http://futuremirex.com/portal/wp-content/uploads/2025/MIREX%20Poster.pdf MIREX 2025 Results Poster (PDF)]

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

====Online Poster====
The deadline of submitting an online poster is Oct 7th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription Results]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:Audio Beat Tracking Results

2025-09-17T06:49:21Z

Junyan: /* Submissions */

== Submissions ==

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG-ApolloBeats 2
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| TBA
| Jingwei Zhao, Rei Nishiyama, Kouhei Sumi, Takuya Fujishima, Akira Maezawa
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 92.98
| 82.75
| 91.63
| 93.66
| 85.79
| 90.57
| 88.27
| 93.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 95.87
| 87.43
| 95.20
| 95.29
| 88.53
| 92.00
| 90.72
| 94.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-16T09:33:01Z

Junyan:

== Submissions ==

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG-ApolloBeats 2
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| TBA
| YAMAHA Corporation
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 92.98
| 82.75
| 91.63
| 93.66
| 85.79
| 90.57
| 88.27
| 93.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats 2
| 95.87
| 87.43
| 95.20
| 95.29
| 88.53
| 92.00
| 90.72
| 94.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-16T04:29:21Z

Junyan:

== Submissions ==

This page is still WIP. More submissions might appear later.

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG2
| Same as KG-ApolloBeats, but not trained on SMC or GTZAN
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| TBA
| YAMAHA Corporation
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 92.98
| 82.75
| 91.63
| 93.66
| 85.79
| 90.57
| 88.27
| 93.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 95.87
| 87.43
| 95.20
| 95.29
| 88.53
| 92.00
| 90.72
| 94.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-14T05:09:08Z

Junyan: /* SMC */

== Submissions ==

This page is still WIP. More submissions might appear later.

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG2
| Same as KG-ApolloBeats, but not trained on SMC or GTZAN
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| TBA
| YAMAHA Corporation
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-14T03:30:17Z

Junyan:

== Submissions ==

This page is still WIP. More submissions might appear later.

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| KG2
| Same as KG-ApolloBeats, but not trained on SMC or GTZAN
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| Beat-U: Multi-Task Music Understanding with Hierarchical Timescales
| TBA
| YAMAHA Corporation
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 250 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 239 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 88.21
| 76.45
| 75.28
| 88.38
| 78.48
| 81.05
| 88.63
| 92.18
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG2
| 58.55
| 45.08
| 25.81
| 68.36
| 39.14
| 50.80
| 46.81
| 61.45
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}
Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-12T08:04:02Z

Junyan:

== Submissions ==

This page is still WIP. More submissions might appear later.

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| BeatU
| TBA
| Jingwei Zhao
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

== Comparison with Previous MIREXes ==

Since this year we have switched to using mir_eval for evaluation, some results may differ from those in previous MIREX editions due to differences in implementation. We confirm that the following metrics remain comparable with previous MIREX results:

* Comparable: F1, Goto, CMLc, CMLt, AMLc, AMLt.
* Not comparable: Cemgil, P-score.

2025:Audio Beat Tracking Results

2025-09-12T07:29:37Z

Junyan: /* Submissions */

== Submissions ==

This page is still WIP. More submissions might appear later.

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| BeatU
| TBA
| Jingwei Zhao
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

2025:Audio Beat Tracking Results

2025-09-12T07:28:26Z

Junyan: /* GTZAN */

== Submissions ==

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| BeatU
| TBA
| Jingwei Zhao
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.

The baseline BeatThis reports different results compared to the paper because it uses a different number of test songs (999 vs. 993).

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

2025:Audio Beat Tracking Results

2025-09-12T07:26:43Z

Junyan:

== Submissions ==

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: CD1
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | QM Tempo Tracker
| [https://vamp-plugins.org/plugin-doc/qm-vamp-plugins.html Link]
|
|-
| Baseline: BeatThis
| Beat This! Accurate Beat Tracking Without DBN Postprocessing
| [https://github.com/CPJKU/beat_this Link]
|
|-
| KG-ApolloBeats
| The 2025 KG Music Beats Tracking System
| TBA
| DingKun Xiao, Haijun Cai, Chuanyi Chen
|-
| BeatU
| BeatU
| TBA
| Jingwei Zhao
|}

== Test Sets ==

* '''GTZAN''': 999 songs from the GTZAN dataset (starting from next year, training on GTZAN will be disallowed)
* '''SMC''': 217 songs from the SMC collection
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

Entries with [*] are trained on this dataset.
== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats*
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis*
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

Entries with [*] are trained on this dataset.

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

2025:MIREX2025 Results

2025-09-11T05:59:32Z

Junyan: /* Online Poster */

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

====Online Poster====
The deadline of submitting an online poster is Oct 7th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

==Overall Results Poster==

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription Results]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:MIREX2025 Results

2025-09-11T05:55:56Z

Junyan: /* MIREX 2025 Onsite/Online Poster Form */

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

====Online Poster====
The deadline of submitting an online poster is September 30th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

==Overall Results Poster==

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription Results]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:MIREX2025 Results

2025-09-11T05:55:47Z

Junyan: /* MIREX 2025 Onsite/Online Poster Form */

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

====Online Poster====
The deadline of submitting an online poster is September 30th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

==Overall Results Poster==

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription Results]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:MIREX2025 Results

2025-09-11T05:55:01Z

Junyan:

==MIREX 2025 Onsite/Online Poster Form==

MIREX participants may present an on-site and/or online poster for their submission. Both of them are optional.

====Online Poster====
The deadline of submitting an online poster is September 30th, 2025.

The online poster will be attached to the MIREX result page of each task.

====Onsite Poster====
The onsite poster will be presented in the Late-breaking/Demo (LBD) session at ISMIR. We have 10 slots in total.

You may present your poster without submitting this form if there are empty slots left.

https://docs.google.com/forms/d/e/1FAIpQLSfLlvLYL-9yuB6x_easntUBFl8kIfxD17NTqeiy7KU0Fkdv_g/viewform

==Overall Results Poster==

==Detailed Results by Task==

Traditional MIR tasks
* [[2025:Audio Chord Estimation Results]] <TC: [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Lyrics Transcription Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan] & [mailto:jj2731@nyu.edu Junyan Jiang]>
* [[2025:Cover Song Identification Results]] <TC: [mailto:x.du@rochester.edu Xingjian Du] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Structure Analysis Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Audio Beat Tracking Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:Audio Key Detection Results]] <TC: [mailto:mwysjtu@gmail.com Wenye Ma] & [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>

Modern MIR Tasks
* [[2025:Symbolic Music Generation Results]] <TC: [mailto:ziyu.wang@nyu.edu Ziyu Wang] & [mailto:jzhao@u.nus.edu Jingwei Zhao]>
* [[2025:Music Audio Generation Results]] <TC: [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Music Description & Captioning Results]] <TC: [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang] & [mailto:ruibiny@alumni.cmu.edu Ruibin Yuan]>
* [[2025:Polyphonic Transcription Results]] <TC: [mailto:ochaturv@purdue.edu Ojas Chaturvedi], [mailto:yunglu@purdue.edu Yung-Hsiang Lu], [mailto:yun98@purdue.edu Kristen Yeon-Ji Yun], [mailto:ziyu.wang@nyu.edu Ziyu Wang], [mailto:yujia.yan@rochester.edu Yujia Yan]>
* [[2025:Song Deepfake Detection Results]] <TC: [mailto:you.zhang@rochester.edu Neil Zhang]>
* [[2025:Music Reasoning QA Results]] <TC: [mailto:yinghao.ma@qmul.ac.uk Yinghao Ma]>
* [[2025:RenCon Results]] (Expressive Piano Performance Rendering Competition) <TC: [mailto:huan.zhang@qmul.ac.uk Huan Zhang]>

2025:Audio Beat Tracking Results

2025-09-11T01:07:10Z

Junyan:

This page is still WIP

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 84.93
| 68.23
| 64.06
| 84.27
| 71.07
| 75.26
| 78.78
| 84.27
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 92.53
| 80.66
| 79.38
| 93.55
| 83.44
| 88.49
| 86.86
| 92.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 89.02
| 80.15
| 72.27
| 88.00
| 76.00
| 79.64
| 84.63
| 90.01
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 81.19
| 69.64
| 62.06
| 79.97
| 65.02
| 66.94
| 83.08
| 86.69
|}

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | BeatU
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

2025:Audio Chord Estimation Results

2025-09-09T12:10:37Z

Junyan:

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| Baseline: ISMIR2019
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| MD1
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
| TBA
| Masayuki Doai
|-
| wu-ensemble
| wu-ensemble
| TBA
| Yiwei Ding, Christof Weiß
|-
| wu-single
| wu-single
| TBA
| Yiwei Ding, Christof Weiß
|-
| YK1
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
| TBA
| Yiming Wu, Kento Yoshida
|-
| BMACE
| A Mamba-Based Model for Automatic Chord Recognition
| TBA
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
|}

= Test Sets =

====Main Test Sets====

The following datasets are served as pure test sets. No system is allowed to train on them.

* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

====Additional Test Sets====

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

= Main Results =

The following datasets are served as pure test sets. No system is allowed to train on them.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 55.72
| 8.88
| 8.70
| 2.52
| 2.45
| 68.16
| 90.86
| 56.60
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.35
| 79.15
| 77.91
| 66.40
| 65.33
| 86.17
| 85.50
| 88.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 81.01
| 78.10
| 75.41
| 64.53
| 62.05
| 85.50
| 85.08
| 87.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 74.64
| 71.97
| 70.72
| 55.06
| 53.96
| 83.19
| 86.29
| 82.20
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 75.77
| 73.14
| 71.74
| 55.41
| 54.15
| 83.16
| 85.44
| 83.08
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 71.06
| 67.18
| 65.09
| 48.88
| 47.06
| 81.60
| 83.14
| 82.71
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 78.61
| 76.39
| 74.72
| 64.15
| 62.65
| 83.39
| 78.57
| 92.78
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 58.92
| 12.59
| 12.29
| 4.52
| 4.34
| 71.62
| 91.05
| 60.47
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.83
| 80.22
| 78.87
| 64.13
| 63.14
| 88.09
| 88.67
| 88.47
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 82.53
| 79.71
| 75.60
| 66.02
| 62.31
| 88.94
| 89.78
| 89.33
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 82.54
| 81.29
| 78.99
| 62.84
| 60.84
| 87.48
| 88.68
| 87.43
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 81.37
| 79.69
| 77.61
| 61.60
| 59.84
| 87.03
| 89.81
| 85.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 77.57
| 74.64
| 71.59
| 56.38
| 53.90
| 86.51
| 87.25
| 87.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 82.00
| 81.16
| 79.69
| 66.97
| 65.77
| 89.04
| 86.43
| 93.49
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 52.38
| 11.90
| 11.65
| 2.37
| 2.23
| 71.98
| 90.23
| 60.42
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 79.34
| 77.10
| 76.07
| 55.59
| 54.71
| 88.00
| 88.13
| 88.20
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 80.13
| 77.03
| 72.85
| 61.24
| 57.26
| 89.42
| 89.71
| 89.49
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 79.58
| 77.58
| 75.57
| 54.36
| 52.58
| 87.22
| 88.44
| 86.55
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 78.87
| 76.56
| 74.66
| 55.35
| 53.60
| 87.19
| 89.30
| 85.70
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.49
| 71.99
| 69.24
| 52.40
| 49.97
| 86.66
| 85.89
| 88.28
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 81.49
| 79.99
| 78.58
| 62.81
| 61.61
| 90.09
| 87.21
| 93.88
|}

= Additional Results =

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.
== Billboard2012 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 58.45
| 9.13
| 9.00
| 2.91
| 2.86
| 69.55
| 92.02
| 57.41
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 85.11
| 83.98
| 82.76
| 74.12
| 73.12
| 88.80
| 88.63
| 89.78
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 85.90
| 84.66
| 81.81
| 77.22
| 74.45
| 88.43
| 87.88
| 89.58
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 78.26
| 77.15
| 75.58
| 59.99
| 58.79
| 84.42
| 87.98
| 82.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 79.23
| 78.21
| 76.76
| 60.23
| 59.07
| 84.87
| 87.19
| 84.24
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 83.69
| 85.33
| 83.48
|}

== RWC-Popular ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | BMACE
| 56.48
| 11.97
| 11.78
| 2.41
| 2.30
| 72.59
| 90.92
| 61.06
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 83.98
| 81.18
| 79.42
| 66.53
| 64.83
| 88.53
| 88.53
| 88.84
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 88.76
| 87.27
| 81.14
| 76.88
| 70.90
| 91.90
| 91.55
| 92.43
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 81.87
| 80.30
| 77.58
| 62.65
| 60.25
| 87.51
| 89.95
| 85.65
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 82.48
| 81.35
| 78.48
| 62.86
| 60.28
| 87.81
| 89.47
| 86.64
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 78.97
| 77.78
| 74.13
| 63.15
| 59.72
| 88.64
| 88.07
| 89.76
|}

= Task Captain's Note =

* Results on Billboard & RWC Popular are competible with previous years.
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results

Submission Guidelines

2025-09-09T04:22:14Z

Junyan: /* Extended Abstract */

==MIREX 2025 Submission Guideline==

=== Submission Site ===

The submission site is available at [http://futuremirex.com/submission MIREX Submission Site]. Please follow the guideline of the site to create a submission.

=== README File ===

Your submission should include a read me file to describe how to build and run your system on a clean machine. This includes:

* OS requirements (specify Linux distribution and version; a Dockerfile is preferred)
* Build dependencies, with a bash script to install them
* Step-by-step instructions for running your submission

=== Extended Abstract ===

When submitting your program(s) for the ISMIR task, please provide a 2–4 page extended abstract in PDF format, following the official [https://github.com/ismir/paper_templates/releases ISMIR LBD template]. This abstract should help both the organizers and the community understand the workings of your algorithm and its application to the task.

* Since this is not a double-blind submission, please replace "anonymous" with the full list of authors.
* '''If you have a full paper associated with your submission''' (e.g., accepted by ISMIR or a preprint), please '''do not submit the full paper directly'''. Instead, provide a 2-page extended abstract that '''cites your paper''' and details any changes or hyperparameters specific to your submission(s), especially if you have multiple entries to the same task.

=== Other Questions ===

For other questions, please contact the task captain or the MIREX organizers.

Submission Guidelines

2025-09-09T04:21:38Z

Junyan: /* MIREX 2025 Submission Guideline */

==MIREX 2025 Submission Guideline==

=== Submission Site ===

The submission site is available at [http://futuremirex.com/submission MIREX Submission Site]. Please follow the guideline of the site to create a submission.

=== README File ===

Your submission should include a read me file to describe how to build and run your system on a clean machine. This includes:

* OS requirements (specify Linux distribution and version; a Dockerfile is preferred)
* Build dependencies, with a bash script to install them
* Step-by-step instructions for running your submission

=== Extended Abstract ===

When submitting your program(s) for the ISMIR task, please provide a 2–4 page extended abstract in PDF format, following the official [https://github.com/ismir/paper_templates/releases ISMIR LBD template]. This abstract should help both the organizers and the community understand the workings of your algorithm and its application to the task.

- Since this is not a double-blind submission, please replace "anonymous" with the full list of authors.

'''If you have a full paper associated with your submission''' (e.g., accepted by ISMIR or a preprint), please '''do not submit the full paper directly'''. Instead, provide a 2-page extended abstract that '''cites your paper''' and details any changes or hyperparameters specific to your submission(s), especially if you have multiple entries to the same task.

=== Other Questions ===

For other questions, please contact the task captain or the MIREX organizers.

2025:Audio Chord Estimation Results

2025-09-09T03:58:31Z

Junyan: /* Submissions */

This page is still WIP. More submissions and descriptions may appear.

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| Baseline: ISMIR2019
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| MD1
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
| TBA
| Masayuki Doai
|-
| wu-ensemble
| wu-ensemble
| TBA
| Yiwei Ding, Christof Weiß
|-
| wu-single
| wu-single
| TBA
| Yiwei Ding, Christof Weiß
|-
| YK1
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
| TBA
| Yiming Wu, Kento Yoshida
|-
| BMACE
| A Mamba-Based Model for Automatic Chord Recognition
| TBA
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
|}

= Test Sets =

====Main Test Sets====

The following datasets are served as pure test sets. No system is allowed to train on them.

* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

====Additional Test Sets====

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

= Main Results =

The following datasets are served as pure test sets. No system is allowed to train on them.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 71.06
| 67.18
| 65.09
| 48.88
| 47.06
| 0.82
| 0.83
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 78.61
| 76.39
| 74.72
| 64.15
| 62.65
| 0.83
| 0.79
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.35
| 79.15
| 77.91
| 66.40
| 65.33
| 0.86
| 0.85
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 74.64
| 71.97
| 70.72
| 55.06
| 53.96
| 0.83
| 0.86
| 0.82
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 75.77
| 73.14
| 71.74
| 55.41
| 54.15
| 0.83
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 81.01
| 78.10
| 75.41
| 64.53
| 62.05
| 0.86
| 0.85
| 0.87
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 77.57
| 74.64
| 71.59
| 56.38
| 53.90
| 0.87
| 0.87
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 82.00
| 81.16
| 79.69
| 66.97
| 65.77
| 0.89
| 0.86
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.83
| 80.22
| 78.87
| 64.13
| 63.14
| 0.88
| 0.89
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 82.54
| 81.29
| 78.99
| 62.84
| 60.84
| 0.87
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 81.37
| 79.69
| 77.61
| 61.60
| 59.84
| 0.87
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 82.53
| 79.71
| 75.60
| 66.02
| 62.31
| 0.89
| 0.90
| 0.89
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.49
| 71.99
| 69.24
| 52.40
| 49.97
| 0.87
| 0.86
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 81.49
| 79.99
| 78.58
| 62.81
| 61.61
| 0.90
| 0.87
| 0.94
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 79.34
| 77.10
| 76.07
| 55.59
| 54.71
| 0.88
| 0.88
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 79.58
| 77.58
| 75.57
| 54.36
| 52.58
| 0.87
| 0.88
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 78.87
| 76.56
| 74.66
| 55.35
| 53.60
| 0.87
| 0.89
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 80.13
| 77.03
| 72.85
| 61.24
| 57.26
| 0.89
| 0.90
| 0.89
|}

= Additional Results =

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

== Billboard2012 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 0.84
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 85.11
| 83.98
| 82.76
| 74.12
| 73.12
| 0.89
| 0.89
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 78.26
| 77.15
| 75.58
| 59.99
| 58.79
| 0.84
| 0.88
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 79.23
| 78.21
| 76.76
| 60.23
| 59.07
| 0.85
| 0.87
| 0.84
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 85.90
| 84.66
| 81.81
| 77.22
| 74.45
| 0.88
| 0.88
| 0.90
|}

== RWC-Popular ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 78.97
| 77.78
| 74.13
| 63.15
| 59.72
| 0.89
| 0.88
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 83.98
| 81.18
| 79.42
| 66.53
| 64.83
| 0.89
| 0.89
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 81.87
| 80.30
| 77.58
| 62.65
| 60.25
| 0.88
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 82.48
| 81.35
| 78.48
| 62.86
| 60.28
| 0.88
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 88.76
| 87.27
| 81.14
| 76.88
| 70.90
| 0.92
| 0.92
| 0.92
|}

= Task Captain's Note =

* Results on Billboard & RWC Popular are competible with previous years.
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results

2025:Audio Beat Tracking Results

2025-09-08T17:06:15Z

Junyan: Created page with "This page is still WIP. == GTZAN == {| class="wikitable" style="text-align:right; |- style="font-weight:bold; text-align:left;" ! style="vertical-align:bottom;" | Group ! st..."

This page is still WIP.

== GTZAN ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 92.65
| 80.60
| 79.01
| 93.48
| 83.22
| 88.34
| 86.79
| 92.68
|- style="vertical-align:bottom;"
| style="text-align:left;" | UTransformer
| 84.42
| 67.84
| 62.97
| 83.78
| 70.23
| 74.52
| 78.18
| 83.77
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 88.71
| 79.82
| 71.37
| 87.71
| 75.21
| 79.02
| 84.13
| 89.72
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 80.64
| 69.17
| 60.93
| 79.40
| 64.04
| 65.94
| 82.65
| 86.24
|}

== SMC ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 74.15
| 57.07
| 32.72
| 84.51
| 53.73
| 72.66
| 55.96
| 76.22
|- style="vertical-align:bottom;"
| style="text-align:left;" | UTransformer
| 53.14
| 40.67
| 14.75
| 63.52
| 27.24
| 41.16
| 30.88
| 47.44
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 71.81
| 55.64
| 27.19
| 82.91
| 49.78
| 69.89
| 51.15
| 72.30
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 33.66
| 26.29
| 6.91
| 45.10
| 9.88
| 13.12
| 17.99
| 29.48
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 91.97
| 81.29
| 88.28
| 92.54
| 79.91
| 88.30
| 82.26
| 91.79
|- style="vertical-align:bottom;"
| style="text-align:left;" | UTransformer
| 92.55
| 82.28
| 89.12
| 93.57
| 83.62
| 90.15
| 85.84
| 93.11
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 90.59
| 79.43
| 81.59
| 91.42
| 64.94
| 84.52
| 66.87
| 87.73
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 76.43
| 67.85
| 64.44
| 74.42
| 55.13
| 59.47
| 71.86
| 83.63
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | F1
! style="vertical-align:bottom;" | Cemgil
! style="vertical-align:bottom;" | Goto
! style="vertical-align:bottom;" | P-score
! style="vertical-align:bottom;" | CMLc
! style="vertical-align:bottom;" | CMLt
! style="vertical-align:bottom;" | AMLc
! style="vertical-align:bottom;" | AMLt
|- style="vertical-align:bottom;"
| style="text-align:left;" | KG-ApolloBeats
| 95.39
| 86.66
| 93.20
| 94.63
| 82.87
| 90.54
| 84.72
| 93.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | UTransformer
| 96.58
| 88.94
| 95.20
| 96.73
| 92.32
| 94.46
| 94.65
| 97.05
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: BeatThis
| 94.00
| 84.08
| 86.80
| 93.15
| 69.66
| 86.64
| 71.39
| 89.57
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: CD1
| 77.38
| 70.76
| 64.40
| 73.55
| 54.98
| 58.71
| 77.28
| 85.29
|}

2025:Audio Chord Estimation Results

2025-09-08T09:03:09Z

Junyan: /* Test Sets */

This page is still WIP. More submissions and descriptions may appear.

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| Baseline: ISMIR2019
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| MD1
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
| TBA
| Muhammad Waseem Akram et al. [*]
|-
| wu-ensemble
| wu-ensemble
| TBA
| Yiwei Ding, Christof Weiß
|-
| wu-single
| wu-single
| TBA
| Yiwei Ding, Christof Weiß
|-
| YK1
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
| TBA
| Yiming Wu, Kento Yoshida
|-
| BMACE
| A Mamba-Based Model for Automatic Chord Recognition
| TBA
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
|}

[*] Please submit an extended abstract containing the full author list.

= Test Sets =

====Main Test Sets====

The following datasets are served as pure test sets. No system is allowed to train on them.

* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

====Additional Test Sets====

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

= Main Results =

The following datasets are served as pure test sets. No system is allowed to train on them.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 71.06
| 67.18
| 65.09
| 48.88
| 47.06
| 0.82
| 0.83
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 78.61
| 76.39
| 74.72
| 64.15
| 62.65
| 0.83
| 0.79
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.35
| 79.15
| 77.91
| 66.40
| 65.33
| 0.86
| 0.85
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 74.64
| 71.97
| 70.72
| 55.06
| 53.96
| 0.83
| 0.86
| 0.82
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 75.77
| 73.14
| 71.74
| 55.41
| 54.15
| 0.83
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 81.01
| 78.10
| 75.41
| 64.53
| 62.05
| 0.86
| 0.85
| 0.87
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 77.57
| 74.64
| 71.59
| 56.38
| 53.90
| 0.87
| 0.87
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 82.00
| 81.16
| 79.69
| 66.97
| 65.77
| 0.89
| 0.86
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.83
| 80.22
| 78.87
| 64.13
| 63.14
| 0.88
| 0.89
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 82.54
| 81.29
| 78.99
| 62.84
| 60.84
| 0.87
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 81.37
| 79.69
| 77.61
| 61.60
| 59.84
| 0.87
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 82.53
| 79.71
| 75.60
| 66.02
| 62.31
| 0.89
| 0.90
| 0.89
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.49
| 71.99
| 69.24
| 52.40
| 49.97
| 0.87
| 0.86
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 81.49
| 79.99
| 78.58
| 62.81
| 61.61
| 0.90
| 0.87
| 0.94
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 79.34
| 77.10
| 76.07
| 55.59
| 54.71
| 0.88
| 0.88
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 79.58
| 77.58
| 75.57
| 54.36
| 52.58
| 0.87
| 0.88
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 78.87
| 76.56
| 74.66
| 55.35
| 53.60
| 0.87
| 0.89
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 80.13
| 77.03
| 72.85
| 61.24
| 57.26
| 0.89
| 0.90
| 0.89
|}

= Additional Results =

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

== Billboard2012 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 0.84
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 85.11
| 83.98
| 82.76
| 74.12
| 73.12
| 0.89
| 0.89
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 78.26
| 77.15
| 75.58
| 59.99
| 58.79
| 0.84
| 0.88
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 79.23
| 78.21
| 76.76
| 60.23
| 59.07
| 0.85
| 0.87
| 0.84
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 85.90
| 84.66
| 81.81
| 77.22
| 74.45
| 0.88
| 0.88
| 0.90
|}

== RWC-Popular ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 78.97
| 77.78
| 74.13
| 63.15
| 59.72
| 0.89
| 0.88
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 83.98
| 81.18
| 79.42
| 66.53
| 64.83
| 0.89
| 0.89
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 81.87
| 80.30
| 77.58
| 62.65
| 60.25
| 0.88
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 82.48
| 81.35
| 78.48
| 62.86
| 60.28
| 0.88
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 88.76
| 87.27
| 81.14
| 76.88
| 70.90
| 0.92
| 0.92
| 0.92
|}

= Task Captain's Note =

* Results on Billboard & RWC Popular are competible with previous years.
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results

2025:Audio Chord Estimation Results

2025-09-08T08:37:08Z

Junyan:

This page is still WIP. More submissions and descriptions may appear.

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| Baseline: ISMIR2019
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
|
|-
| MD1
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
| TBA
| Muhammad Waseem Akram et al. [*]
|-
| wu-ensemble
| wu-ensemble
| TBA
| Yiwei Ding, Christof Weiß
|-
| wu-single
| wu-single
| TBA
| Yiwei Ding, Christof Weiß
|-
| YK1
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
| TBA
| Yiming Wu, Kento Yoshida
|-
| BMACE
| A Mamba-Based Model for Automatic Chord Recognition
| TBA
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
|}

[*] Please submit an extended abstract containing the full author list.

= Test Sets =

====Main Test Sets====
* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

====Additional Test Sets====

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.
* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

= Main Results =

The following datasets are served as pure test sets. No system is allowed to train on them.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 71.06
| 67.18
| 65.09
| 48.88
| 47.06
| 0.82
| 0.83
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 78.61
| 76.39
| 74.72
| 64.15
| 62.65
| 0.83
| 0.79
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.35
| 79.15
| 77.91
| 66.40
| 65.33
| 0.86
| 0.85
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 74.64
| 71.97
| 70.72
| 55.06
| 53.96
| 0.83
| 0.86
| 0.82
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 75.77
| 73.14
| 71.74
| 55.41
| 54.15
| 0.83
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 81.01
| 78.10
| 75.41
| 64.53
| 62.05
| 0.86
| 0.85
| 0.87
|}

== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 77.57
| 74.64
| 71.59
| 56.38
| 53.90
| 0.87
| 0.87
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 82.00
| 81.16
| 79.69
| 66.97
| 65.77
| 0.89
| 0.86
| 0.93
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 81.83
| 80.22
| 78.87
| 64.13
| 63.14
| 0.88
| 0.89
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 82.54
| 81.29
| 78.99
| 62.84
| 60.84
| 0.87
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 81.37
| 79.69
| 77.61
| 61.60
| 59.84
| 0.87
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 82.53
| 79.71
| 75.60
| 66.02
| 62.31
| 0.89
| 0.90
| 0.89
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.49
| 71.99
| 69.24
| 52.40
| 49.97
| 0.87
| 0.86
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ISMIR2019
| 81.49
| 79.99
| 78.58
| 62.81
| 61.61
| 0.90
| 0.87
| 0.94
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 79.34
| 77.10
| 76.07
| 55.59
| 54.71
| 0.88
| 0.88
| 0.88
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 79.58
| 77.58
| 75.57
| 54.36
| 52.58
| 0.87
| 0.88
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 78.87
| 76.56
| 74.66
| 55.35
| 53.60
| 0.87
| 0.89
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 80.13
| 77.03
| 72.85
| 61.24
| 57.26
| 0.89
| 0.90
| 0.89
|}

= Additional Results =

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

== Billboard2012 ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 0.84
| 0.85
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 85.11
| 83.98
| 82.76
| 74.12
| 73.12
| 0.89
| 0.89
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 78.26
| 77.15
| 75.58
| 59.99
| 58.79
| 0.84
| 0.88
| 0.83
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 79.23
| 78.21
| 76.76
| 60.23
| 59.07
| 0.85
| 0.87
| 0.84
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 85.90
| 84.66
| 81.81
| 77.22
| 74.45
| 0.88
| 0.88
| 0.90
|}

== RWC-Popular ==

{| class="wikitable" style="text-align:right;
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 78.97
| 77.78
| 74.13
| 63.15
| 59.72
| 0.89
| 0.88
| 0.90
|- style="vertical-align:bottom;"
| style="text-align:left;" | MD1
| 83.98
| 81.18
| 79.42
| 66.53
| 64.83
| 0.89
| 0.89
| 0.89
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-ensemble
| 81.87
| 80.30
| 77.58
| 62.65
| 60.25
| 0.88
| 0.90
| 0.86
|- style="vertical-align:bottom;"
| style="text-align:left;" | wu-single
| 82.48
| 81.35
| 78.48
| 62.86
| 60.28
| 0.88
| 0.89
| 0.87
|- style="vertical-align:bottom;"
| style="text-align:left;" | YK1
| 88.76
| 87.27
| 81.14
| 76.88
| 70.90
| 0.92
| 0.92
| 0.92
|}

= Task Captain's Note =

* Results on Billboard & RWC Popular are competible with previous years.
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results