2024:Singing Voice Deepfake Detection - Revision history

Ldzhangyx: /* Submission */

2024-10-10T16:22:00Z

‎Submission

2024-09-27T12:25:23Z

‎Dataset

2024-09-27T12:24:06Z

‎Task Description

2024-09-26T14:39:50Z

‎Download

2024-09-26T14:38:37Z

‎Download

2024-09-26T14:37:04Z

‎Task Description

2024-09-15T02:20:41Z

‎Download

2024-09-10T12:59:46Z

‎Submission

2024-09-10T12:27:28Z

‎Submission

2024-09-07T23:01:49Z

‎Baseline

@@ Line 58: / Line 58: @@
 = Submission =
-* '''Submission Deadline: October 15, AOE'''
+* '''Submission Deadline: October 20, AOE'''
 ;Results submission
@@ Line 72: / Line 72: @@
 ;Workshop presentation
 :We will invite top-ranked participants to present their work during the workshop session. The format will be hybrid to accommodate remote participation.

@@ Line 19: / Line 19: @@
 ;Description
-:The WildSVDD dataset is an extension of the SingFake dataset, now expanded to include a more diverse and comprehensive collection of real and AI-generated singing voice clips. We gathered data annotations from social media platforms. The annotators, who were familiar with the singers they covered, manually verified the user-specified labels during the annotation process to ensure accuracy, especially in cases where the singer(s) did not actually perform certain songs. We cross-checked the annotations against song titles and descriptions and manually reviewed any discrepancies for further verification.
+:The WildSVDD dataset is an extension of the SingFake dataset, now expanded to include a more diverse and comprehensive collection of real and AI-generated singing voice clips. We gathered data annotations from social media platforms. The annotators, who were familiar with the singers they covered, manually verified the user-specified labels during the annotation process to ensure accuracy, especially in cases where the singer(s) did not actually perform certain songs. We cross-checked the annotations against song titles and descriptions and manually reviewed any discrepancies for further verification. See "Download" section for details.
 ;Description of Audio Files

← Older revision		Revision as of 12:24, 27 September 2024
Line 13:		Line 13:

	:[3] Zang, Yongyi, Jiatong Shi, You Zhang, Ryuichi Yamamoto, Jionghao Han, Yuxun Tang, Shengyuan Xu et al. “CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection.” In Proc. Interspeech, pp. 4783-4787, 2024. https://doi.org/10.21437/Interspeech.2024-2242		:[3] Zang, Yongyi, Jiatong Shi, You Zhang, Ryuichi Yamamoto, Jionghao Han, Yuxun Tang, Shengyuan Xu et al. “CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection.” In Proc. Interspeech, pp. 4783-4787, 2024. https://doi.org/10.21437/Interspeech.2024-2242
		+
		+	Contact: [mailto:you.zhang@rochester.edu Neil Zhang] & [mailto:yixiao.zhang@qmul.ac.uk Yixiao Zhang]

	= Dataset =		= Dataset =

@@ Line 48: / Line 48: @@
 * Segmentation tool: [SingFake GitHub](https://github.com/yongyizang/SingFake/tree/main/dataset)
-Participants are encouraged to use the provided tools to download and segment song clips to ensure consistency in evaluation. If you have concerns about downloading data, please reach out to svddchallenge@gmail.com
+Participants are encouraged to use the provided tools to download and segment song clips to ensure consistency in evaluation. If you have concerns about downloading data, please reach out to [mailto:svddchallenge@gmail.com svddchallenge@gmail.com].
 = Rules =

@@ Line 48: / Line 48: @@
 * Segmentation tool: [SingFake GitHub](https://github.com/yongyizang/SingFake/tree/main/dataset)
-Participants are encouraged to use the provided tools to download and segment song clips to ensure consistency in evaluation.
+Participants are encouraged to use the provided tools to download and segment song clips to ensure consistency in evaluation. If you have concerns about downloading data, please reach out to svddchallenge@gmail.com
 = Rules =

@@ Line 1: / Line 1: @@
 = Task Description =
-The WildSVDD challenge aims to detect AI-generated singing voices in real-world scenarios. The task involves distinguishing authentic human-sung songs from AI-generated deepfake songs at the clip level. Participants are required to identify whether each segmented clip contains a genuine singer or an AI-generated fake singer. The developed systems are expected to account for the complexities introduced by background music and various musical contexts.
+The WildSVDD challenge aims to detect AI-generated singing voices in real-world scenarios. The task involves distinguishing authentic human-sung songs from AI-generated deepfake songs at the clip level. Participants are required to identify whether each segmented clip contains a genuine singer or an AI-generated fake singer. The developed systems are expected to account for the complexities introduced by background music and various musical contexts. For more information about our prior work, please visit: https://main.singfake.org/
 ;Background

@@ Line 45: / Line 45: @@
 * Dataset download: [Zenodo WildSVDD](https://zenodo.org/records/10893604)
-* Download tools: https://pastebin.com/YhpYXT9z, https://cobalt.tools/, https://github.com/ytdl-org/youtube-dl, https://github.com/yt-dlp/yt-dlp, https://www.locoloader.com/bilibili-video-downloader/
+* Download tools: https://pastebin.com/bFeruNA0, https://cobalt.tools/, https://github.com/ytdl-org/youtube-dl, https://github.com/yt-dlp/yt-dlp, https://www.locoloader.com/bilibili-video-downloader/
 * Segmentation tool: [SingFake GitHub](https://github.com/yongyizang/SingFake/tree/main/dataset)

← Older revision		Revision as of 12:59, 10 September 2024
Line 55:		Line 55:

	= Submission =		= Submission =
		+
		+	* '''Submission Deadline: October 15, AOE'''

	;Results submission		;Results submission

@@ Line 64: / Line 64: @@
 ;Research paper submission
-:Participants are encouraged to submit a research paper to the late-breaking demo session at ISMIR 2024. https://ismir2024.ismir.net/call-for-late-breaking-demos
+:Participants are encouraged to submit a research paper to the '''MIREX track''' at ISMIR 2024.
 ;Workshop presentation
 :We will invite top-ranked participants to present their work during the workshop session. The format will be hybrid to accommodate remote participation.

@@ Line 34: / Line 34: @@
 :[2] SingGraph: https://github.com/xjchenGit/SingGraph
-:[3]
+:[3] SVDD 2024@SLT: https://arxiv.org/abs/2408.16132
 = Metrics =