SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan

You Zhang, Yongyi Zang, Jiatong Shi, Ryuichi Yamamoto, Jionghao Han +3 more
5/8/2024
eess.AScs.AIcs.MM

No official code found. Best implementation: SVDDChallenge/CtrSVDD2024_Baseline (30 stars, last commit 2024-11-16).

Abstract

The rapid advancement of AI-generated singing voices, which now closely mimic natural human singing and align seamlessly with musical scores, has led to heightened concerns for artists and the music industry. Unlike spoken voice, singing voice presents unique challenges due to its musical nature and the presence of strong background music, making singing voice deepfake detection (SVDD) a specialized field requiring focused attention. To promote SVDD research, we recently proposed the "SVDD Challenge," the very first research challenge focusing on SVDD for lab-controlled and in-the-wild bonafide and deepfake singing voice recordings. The challenge will be held in conjunction with the 2024 IEEE Spoken Language Technology Workshop (SLT 2024).

View on arXivView PDF

Code Implementations(1)

SVDDChallenge/CtrSVDD2024_BaselineCommunity100%

Baseline system for SVDD 2024 Challenge CtrSVDD track

304Python, Jupyter NotebookJan 8, 20241 years ago

Similar Papers

Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024

84% match1 repo82024

Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection

84% match2024

Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024

82% match1 repo162025

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge

81% match2024

SONICS: Synthetic Or Not - Identifying Counterfeit Songs

81% match1 repo592026

PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset

81% match1 repo102024

Cite this paper

@article{zhang2024svdd,
  title  = {SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan},
  author = {You Zhang and Yongyi Zang and Jiatong Shi and Ryuichi Yamamoto and Jionghao Han and Yuxun Tang and Tomoki Toda and Zhiyao Duan},
  year   = {2024},
  eprint = {2405.05244},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.05244v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.05244.svg)](https://codeofpaper.com/paper/2405.05244)

Discussion