The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge aims to benchmark and advance zero-shot spontaneous style voice cloning, particularly focusing on generating spontaneous behaviors in conversational speech. The challenge comprises two tracks: an unconstrained track without limitation on data and model usage, and a constrained track only allowing the use of constrained open-source datasets. A 100-hour high-quality conversational speech dataset is also made available with the challenge. This paper details the data, tracks, submitted systems, evaluation results, and findings.
@article{arxiv.2411.00064,
title = {The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings},
author = {Kangxiang Xia and Dake Guo and Jixun Yao and Liumeng Xue and Hanzhao Li and Shuai Wang and Zhao Guo and Lei Xie and Qingqing Zhang and Lei Luo and Minghui Dong and Peng Sun},
journal= {arXiv preprint arXiv:2411.00064},
year = {2024}
}