The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings
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. The challenge's official website is https://www.magicdatatech.com/iscslp-2024.
Authors
- Liumeng Xue (ORCID: https://orcid.org/0000-0003-2815-8494)
- Jixun Yao (ORCID: https://orcid.org/0000-0002-5324-7360)
- Hanzhao Li (ORCID: https://orcid.org/0009-0005-3215-7517)
- Peng Sun (ORCID: https://orcid.org/0000-0002-4782-0693)
- Shuai Wang (ORCID: https://orcid.org/0000-0002-5073-3371)
- Qingqing Zhang (ORCID: https://orcid.org/0009-0007-9373-3527)
- Minghui Dong (ORCID: https://orcid.org/0000-0002-6965-2862)
- Lei Xie (ORCID: https://orcid.org/0000-0001-8234-0823)
- Zhao Guo (ORCID: https://orcid.org/0000-0003-1477-0842)
- Dake Guo
- Lei Luo (ORCID: https://orcid.org/0000-0001-8620-6410)
- Kangxiang Xia
Institutions
- Northwestern Polytechnical University (CN)
- Institute for Infocomm Research (SG)
- Shenzhen Research Institute of Big Data (CN)
- China Computer Federation (CN)
- Chinese University of Hong Kong, Shenzhen (CN)
Publication Details
- Published
- 2024-11-07
- DOI
- https://doi.org/10.1109/iscslp63861.2024.10800694
- Citations
- 2
- Primary Topic
- AI in Service Interactions
- Type
- article
- Field-Weighted Citation Impact
- 0.69