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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, You, Zang, Yongyi, Shi, Jiatong, Yamamoto, Ryuichi, Han, Jionghao, Tang, Yuxun, Toda, Tomoki, Duan, Zhiyao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909195763187712
author Zhang, You
Zang, Yongyi
Shi, Jiatong
Yamamoto, Ryuichi
Han, Jionghao
Tang, Yuxun
Toda, Tomoki
Duan, Zhiyao
author_facet Zhang, You
Zang, Yongyi
Shi, Jiatong
Yamamoto, Ryuichi
Han, Jionghao
Tang, Yuxun
Toda, Tomoki
Duan, Zhiyao
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2405_05244
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
Zhang, You
Zang, Yongyi
Shi, Jiatong
Yamamoto, Ryuichi
Han, Jionghao
Tang, Yuxun
Toda, Tomoki
Duan, Zhiyao
Audio and Speech Processing
Artificial Intelligence
Multimedia
Sound
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).
title SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan
topic Audio and Speech Processing
Artificial Intelligence
Multimedia
Sound
url https://arxiv.org/abs/2405.05244