Work

SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge (CtrSVDD Track, Test Set)

Year: 2023

Type: preprint

Abstract: For more information about SVDD Challenge 2024, please refer to https://challenge.singfake.org/.We have released the training and development set here and other relevant scripts on GitHub (https://github.com/SVDDChallenge/SVDD_Utils). For evaluation, we will provide a test set with undisclosed labels at a later date and ask teams to score each utterance. Using the submitted scores, we will calculate and rank participant systems on EER.Please note that due to licensing issues, the training and development set here is not complete. Please follow the instructions detailed in the GitHub repository to complete the generation process of the dataset.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2309.07525

Authors: Zhang, You, Zang, Yongyi, Shi, Jiatong, Yamamoto, Ryuichi, Han, Jionghao, Tang, Yuxun, Xu, Shengyuan, Zhao, Wenxiao, Guo, Jing, Toda, Tomoki, Duan, Zhiyao

Institutions: University of Rochester, Carnegie Mellon University, Nagoya University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Science Foundation

Awards: CAREER: Human-Computer Collaborative Music Making, Collaborative Research: FW-HTF-R: Toward an Ecosystem of Artificial Intelligence-Powered Music Production (TEAMuP), NRT-HDR: Interdisciplinary Graduate Training in the Science, Technology, and Applications of Augmented and Virtual Reality

OpenAlex ID: W4386794738

Cites:

Cited by: 1

Related to: 10