SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
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).
Cite
@article{arxiv.2405.05244,
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},
journal= {arXiv preprint arXiv:2405.05244},
year = {2024}
}
Comments
Evaluation plan of the SVDD Challenge @ SLT 2024