Difference between revisions of "2007:Audio Classical Composer Identification"
IMIRSELBot (talk | contribs) m (Robot: Automated text replacement (-\[\[([A-Z][^:]+)\]\] +2007:\1)) |
|||
| (8 intermediate revisions by 4 users not shown) | |||
| Line 1: | Line 1: | ||
| + | =FINAL 2007 AUDIO CLASSICAL COMPOSER IDENTIFICATION EVALUATION SCENARIO OVERVIEW= | ||
| + | This section is put here to clarify what will happen for this year's "beta" run of the Audio Classical Composer (ACC) ID task. | ||
| + | |||
| + | # We will operate the ACC task as a classic train-test classification task. | ||
| + | # We will 3-fold the runs. | ||
| + | # We will hand-craft the n-fold test-train split lists. | ||
| + | # Audio files: 30 sec., 22kHz, mono, 16 bit | ||
| + | |||
| + | Do take a look at the [[2007:Audio Genre Classification]] task wiki as we are basing the underlying structure of this task on Audio Genre. In fact, an Audio Genre submission should work out of the box with Audio Mood Classification. Note: we really want folks to do a FEATURE EXTRACTION phase first against all the files and then have these features cached some place for re-use during the TRAIN-TEST phase. This way we can really speed up the n-fold processing. Thus, like GENRE, we need to pass three input files to your algos: | ||
| + | |||
| + | ==== 1. Feature extraction list file ==== | ||
| + | The list file passed for feature extraction will a simple ASCII list | ||
| + | file. This file will contain one path per line with no header line. | ||
| + | |||
| + | ==== 2. Training list file ==== | ||
| + | The list file passed for model training will be a simple ASCII list | ||
| + | file. This file will contain one path per line, followed by a tab character and | ||
| + | the genre label, again with no header line. | ||
| + | |||
| + | E.g. <example path and filename>\t<mood classification> | ||
| + | |||
| + | ==== 3. Test (classification) list file ==== | ||
| + | The list file passed for testing classification will be a simple ASCII list | ||
| + | file identical in format to the Feature extraction list file. This file will | ||
| + | contain one path per line with no header line. | ||
| + | |||
| + | ==== Classification output files ==== | ||
| + | Participating algorithms should produce a simple ASCII list file identical in | ||
| + | format to the Training list file. This file will contain one path per line, | ||
| + | followed by a tab character and the genre label, again with no header line. | ||
| + | E.g.: | ||
| + | <example path and filename>\t<composer_name> | ||
| + | |||
| + | The path to which this list file should be written must be accepted as a | ||
| + | parameter on the command line. | ||
| + | |||
| + | ******************************************** | ||
| + | |||
== Introduction == | == Introduction == | ||
This task is intended to be a sub-task of artist identification and will be run in exactly the same format on a different database. | This task is intended to be a sub-task of artist identification and will be run in exactly the same format on a different database. | ||
| Line 10: | Line 48: | ||
Related MIREX 2007 task proposals: | Related MIREX 2007 task proposals: | ||
| − | * [[Audio Artist Identification]] | + | * [[2007:Audio Artist Identification]] |
| − | * [[Audio Genre Classification]] | + | * [[2007:Audio Genre Classification]] |
Please feel free to edit this page. | Please feel free to edit this page. | ||
== Data == | == Data == | ||
| − | + | 2772 30-second 22.05 kHz mono wav clips organised into 11 "classical" composers (252 clips per composer). At present the database contains tracks for: | |
* Bach | * Bach | ||
* Beethoven | * Beethoven | ||
| Line 23: | Line 61: | ||
* Dvorak | * Dvorak | ||
* Handel | * Handel | ||
| − | * | + | * Haydn |
* Mendelssohn | * Mendelssohn | ||
* Mozart | * Mozart | ||
| Line 30: | Line 68: | ||
== Evaluation == | == Evaluation == | ||
| − | The evaluation procedures used for artist identification will also be used for this task. Please see [[Audio Artist Identification]] for details. | + | The evaluation procedures used for artist identification will also be used for this task. Please see [[2007:Audio Artist Identification]] for details. |
== Submission format == | == Submission format == | ||
Submission to this task will have to conform to a specified format detailed | Submission to this task will have to conform to a specified format detailed | ||
| − | in the [[Audio Artist Identification]] proposal. | + | in the [[2007:Audio Artist Identification]] proposal. |
=== Audio formats === | === Audio formats === | ||
| Line 45: | Line 83: | ||
=== Implementation details === | === Implementation details === | ||
| − | Please see [[Audio Artist Identification]] for details. | + | Please see [[2007:Audio Artist Identification]] for details. |
=== I/O formats === | === I/O formats === | ||
| − | Please see [[Audio Artist Identification]] for details. | + | Please see [[2007:Audio Artist Identification]] for details. |
=== Packaging submissions === | === Packaging submissions === | ||
| − | Please see [[Audio Artist Identification]] for details. | + | Please see [[2007:Audio Artist Identification]] for details. |
=== Pre-trained submissions === | === Pre-trained submissions === | ||
| Line 74: | Line 112: | ||
* Thomas Lidy (''lastname''@ifs.tuwien.ac.at) | * Thomas Lidy (''lastname''@ifs.tuwien.ac.at) | ||
| + | * Lei Wang (leiwang at hitic.ia.ac.cn) | ||
* .... | * .... | ||
Latest revision as of 15:57, 13 May 2010
Contents
- 1 FINAL 2007 AUDIO CLASSICAL COMPOSER IDENTIFICATION EVALUATION SCENARIO OVERVIEW
- 1.1 1. Feature extraction list file
- 1.2 2. Training list file
- 1.3 3. Test (classification) list file
- 1.4 Classification output files
- 1.5 Introduction
- 1.6 Status
- 1.7 Data
- 1.8 Evaluation
- 1.9 Submission format
- 1.10 Time and hardware limits
- 1.11 Submission opening date
- 1.12 Submission closing date
- 1.13 Participants
FINAL 2007 AUDIO CLASSICAL COMPOSER IDENTIFICATION EVALUATION SCENARIO OVERVIEW
This section is put here to clarify what will happen for this year's "beta" run of the Audio Classical Composer (ACC) ID task.
- We will operate the ACC task as a classic train-test classification task.
- We will 3-fold the runs.
- We will hand-craft the n-fold test-train split lists.
- Audio files: 30 sec., 22kHz, mono, 16 bit
Do take a look at the 2007:Audio Genre Classification task wiki as we are basing the underlying structure of this task on Audio Genre. In fact, an Audio Genre submission should work out of the box with Audio Mood Classification. Note: we really want folks to do a FEATURE EXTRACTION phase first against all the files and then have these features cached some place for re-use during the TRAIN-TEST phase. This way we can really speed up the n-fold processing. Thus, like GENRE, we need to pass three input files to your algos:
1. Feature extraction list file
The list file passed for feature extraction will a simple ASCII list file. This file will contain one path per line with no header line.
2. Training list file
The list file passed for model training will be a simple ASCII list file. This file will contain one path per line, followed by a tab character and the genre label, again with no header line.
E.g. <example path and filename>\t<mood classification>
3. Test (classification) list file
The list file passed for testing classification will be a simple ASCII list file identical in format to the Feature extraction list file. This file will contain one path per line with no header line.
Classification output files
Participating algorithms should produce a simple ASCII list file identical in format to the Training list file. This file will contain one path per line, followed by a tab character and the genre label, again with no header line. E.g.:
<example path and filename>\t<composer_name>
The path to which this list file should be written must be accepted as a parameter on the command line.
Introduction
This task is intended to be a sub-task of artist identification and will be run in exactly the same format on a different database.
The task is to identify the composer of a number of pieces of classical music from the baroque, classical and romantic periods. This task is distinct from artist identification in that the performer of each piece may be varied.
Due to the fact that the submission format is likely to be identical to that of audio artist identification and genre classification - participants to either task may also enter their algorithm into this task.
Status
A provisional specification of the composer identification task is detailed below. This proposal may be refined based on feedback from the particpants.
Related MIREX 2007 task proposals:
Please feel free to edit this page.
Data
2772 30-second 22.05 kHz mono wav clips organised into 11 "classical" composers (252 clips per composer). At present the database contains tracks for:
- Bach
- Beethoven
- Brahms
- Chopin
- Dvorak
- Handel
- Haydn
- Mendelssohn
- Mozart
- Schubert
- Vivaldi
Evaluation
The evaluation procedures used for artist identification will also be used for this task. Please see 2007:Audio Artist Identification for details.
Submission format
Submission to this task will have to conform to a specified format detailed in the 2007:Audio Artist Identification proposal.
Audio formats
Participating algorithms will have to read audio in the following format:
- Sample rate: 22 KHz
- Sample size: 16 bit
- Number of channels: 1 (mono)
- Encoding: WAV
Implementation details
Please see 2007:Audio Artist Identification for details.
I/O formats
Please see 2007:Audio Artist Identification for details.
Packaging submissions
Please see 2007:Audio Artist Identification for details.
Pre-trained submissions
Pre-trained submissions to this task will be accepted - however they will have to ensure that they return the correct classification labels (as listed in the hierachy file).
Time and hardware limits
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions will be specified.
A hard limit of 24 hours will be imposed on feature extraction times.
A hard limit of 24 hours will be imposed on each training/classificaiton cycle, leading to a total runtime limit of 72 hours.
Submission opening date
14th August 2007 - provisional
Submission closing date
28th August 2007 - provisional
Participants
If you think there is a slight chance that you might want to participate please add your name and email address here.
- Thomas Lidy (lastname@ifs.tuwien.ac.at)
- Lei Wang (leiwang at hitic.ia.ac.cn)
- ....
