The SVDD task aims to detect AI-generated singing voices, which is an emerging issue within the music industry that requires specialized solutions.
The SVDD task aims to detect AI-generated singing voices, which is an emerging issue within the music industry that requires specialized solutions.
Detect AI-generated singing voices in the wild, addressing real-world scenarios and diverse audio conditions.
Develop advanced algorithms for singing voice deepfake detection, pushing the boundaries of audio forensics.
Explore our datasets and publications related to Singing Voice Deepfake Detection.
Newly updated from SingFake dataset for singing voice deepfake detection in the wild.
Includes baseline system and dataset for singing voice deepfake detection.
Provides baseline system and dataset for singing voice deepfake detection.
University of Rochester
you.zhang@rochester.edu
University of Rochester
yongyi.zang@rochester.edu
Carnegie Mellon University
jiatongs@andrew.cmu.edu
Nagoya University
zryuichi@gmail.com
Nagoya University
tomoki@icts.nagoya-u.ac.jp
University of Rochester
zhiyao.duan@rochester.edu