{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:48:47Z","timestamp":1777639727110,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746682","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6182-6186","source":"Crossref","is-referenced-by-count":140,"title":["WENETSPEECH: A 10000+ Hours Multi-Domain Mandarin Corpus for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Binbin","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science"}]},{"given":"Hang","family":"Lv","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science"}]},{"given":"Qijie","family":"Shao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Mobvoi Inc."}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Shell Shell Technology Co., Ltd."}]},{"given":"Hui","family":"Bu","sequence":"additional","affiliation":[{"name":"Beijing Shell Shell Technology Co., Ltd."}]},{"given":"Xiaoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Mobvoi Inc."}]},{"given":"Chenchen","family":"Zeng","sequence":"additional","affiliation":[{"name":"Mobvoi Inc."}]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"Mobvoi Inc."}]},{"given":"Zhendong","family":"Peng","sequence":"additional","affiliation":[{"name":"Mobvoi Inc."}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref38","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Annual Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref33","article-title":"Jieba chinese word segmentation tool","author":"sun","year":"2012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref40","article-title":"The ASRU 2019 mandarin-english code-switching speech recognition challenge: open datasets, tracks, methods and results","author":"shi","year":"2020","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref11","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/29.45616"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proceedings of the ACM International Conference on Machine Learning (ICML)"},{"key":"ref27","article-title":"Aishell-2: Transforming mandarin ASR research into industrial scale","author":"du","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"International Conference on Machine Learning (ICML) Representation Learning Workshop"},{"key":"ref8","first-page":"4578","article-title":"Efficient conformer with prob-sparse attention mechanism for end-to-endspeech recognition","author":"wang","year":"2021","journal-title":"Conference of the International Speech Communication Association (InterSpeech)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref9","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Annual Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Annual Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Annual Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref24","article-title":"The people’s speech: A large-scale diverse english speech recognition dataset for commercial usage","author":"galvez","year":"2021","journal-title":"Annual Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746682.pdf?arnumber=9746682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:18Z","timestamp":1660594038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746682","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}