WENETSPEECH: A 10000+ HOURS MULTI-DOMAIN MANDARIN CORPUS FOR SPEECH RECOGNITION

Binbin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di Wu, Zhendong Peng

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

149 Scopus citations

Abstract

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of speaking styles, scenarios, domains, topics and noisy conditions. An optical character recognition (OCR) method is introduced to generate the audio/text segmentation candidates for the YouTube data on the corresponding video subtitles, while a high-quality ASR transcription system is used to generate audio/text pair candidates for the Podcast data. Then we propose a novel end-to-end label error detection approach to further validate and filter the candidates. We also provide three manually labelled high-quality test sets along with WenetSpeech for evaluation - Dev for cross-validation purpose in training, Test Net, collected from Internet for matched test, and Test Meeting, recorded from real meetings for more challenging mismatched test. Baseline systems trained with WenetSpeech are provided for three popular speech recognition toolkits, namely Kaldi, ESPnet, and WeNet, and recognition results on the three test sets are also provided as benchmarks. To the best of our knowledge, WenetSpeech is the current largest open-source Mandarin speech corpus with transcriptions, which benefits research on production-level speech recognition.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6182-6186
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore
Duration: 22 May 202227 May 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityHybrid
Period22/05/2227/05/22

Keywords

  • automatic speech recognition
  • corpus
  • multi-domain

Fingerprint

Dive into the research topics of 'WENETSPEECH: A 10000+ HOURS MULTI-DOMAIN MANDARIN CORPUS FOR SPEECH RECOGNITION'. Together they form a unique fingerprint.

Cite this