The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings

Kangxiang Xia, Dake Guo, Jixun Yao, Liumeng Xue, Hanzhao Li, Shuai Wang, Zhao Guo, Lei Xie, Qingqing Zhang, Lei Luo, Minghui Dong, Peng Sun

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2024 14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024
EditorsYanmin Qian, Qin Jin, Zhijian Ou, Zhenhua Ling, Zhiyong Wu, Ya Li, Lei Xie, Jianhua Tao
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages506-510
Number of pages5
ISBN (Electronic)9798331516826
DOIs
StatePublished - 2024
Event14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024 - Beijing, China
Duration: 7 Nov 202410 Nov 2024

Publication series

Name2024 14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024

Conference

Conference14th International Symposium on Chinese Spoken Language Processing, ISCSLP 2024
Country/TerritoryChina
CityBeijing
Period7/11/2410/11/24

Keywords

  • conversational speech synthesis
  • spontaneous behavior
  • voice clone

Fingerprint

Dive into the research topics of 'The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings'. Together they form a unique fingerprint.

Cite this