{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:38Z","timestamp":1775229758374,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094787","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Self-Supervised Learning with Bi-Label Masked Speech Prediction for Streaming Multi-Talker Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zili","family":"Huang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft, One Microsoft Way,Redmond,WA,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref14","article-title":"Decoar 2.0: Deep contextualized acoustic representations with vector quantization","author":"ling","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref10","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref17","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"ming-wei","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref16","first-page":"2797","article-title":"Serialized output training for end-to-end overlapped speech recognition","author":"kanda","year":"2020","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3045556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","first-page":"5904","article-title":"Developing real-time streaming transformer transducer for speech recognition on large-scale dataset","author":"chen","year":"2021","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"ref21","first-page":"241","article-title":"Permutation invariant training of deep models for speaker-independent multi-talker speech separation","author":"yu","year":"2017","journal-title":"ICASSP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-703"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref9","first-page":"293","article-title":"Analysis of overlaps in meetings by dialog factors, hot spots, speakers, and collection site: Insights for automatic speech recognition","author":"\u00e7etin","year":"2006","journal-title":"InterSpeech"},{"key":"ref4","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":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094787.pdf?arnumber=10094787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:17Z","timestamp":1699902017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094787","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}