{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:05:27Z","timestamp":1772039127398,"version":"3.50.1"},"reference-count":55,"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\/icassp43922.2022.9746270","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9156-9160","source":"Crossref","is-referenced-by-count":23,"title":["Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yu","sequence":"first","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"AISHELL Foundation"}]},{"given":"Yihui","family":"Fu","sequence":"additional","affiliation":[{"name":"AISHELL Foundation"}]},{"given":"Zhihao","family":"Du","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Weilong","family":"Huang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"AISHELL Foundation"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University,Center for Cognitive and Brain Sciences,Department of Computer Science and Engineering,USA"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"A*STAR,Institute for Infocomm Research,Aural and Language Intelligence Department,Singapore"}]},{"given":"Zhijie","family":"Yan","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,China"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab,Singapore"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Shell Shell Technology Co., Ltd.,Beijing,China"}]},{"given":"Hui","family":"Bu","sequence":"additional","affiliation":[{"name":"Beijing Shell Shell Technology Co., Ltd.,Beijing,China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref38","first-page":"100","article-title":"The AMI meeting corpus","volume":"88","author":"mccowan","year":"2005","journal-title":"Proc ICMT"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414464"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref30","article-title":"Snri target training for joint speech enhancement and recognition","author":"koizumi","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref35","first-page":"3735","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","volume":"33","author":"shi","year":"2020","journal-title":"Proc NIPS"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1981"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953173"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"},{"key":"ref1","first-page":"369","article-title":"The rich transcription 2005 spring meeting recognition evaluation","author":"fiscus","year":"2005","journal-title":"Proc MLMI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-58"},{"key":"ref21","article-title":"The third dihard diarization challenge","author":"ryant","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-750"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref26","first-page":"2472","article-title":"DCCRN: Deep complex convolution recurrent network for phase-aware speech enhancement","author":"hu","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref25","article-title":"Recent advances in end-to-end automatic speech recognition","author":"li","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747067"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747381"},{"key":"ref54","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"wu","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746246"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383490"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2456","DOI":"10.21437\/Interspeech.2017-305","article-title":"Recognizing multi-talker speech with permutation invariant training","author":"yu","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref11","first-page":"184","article-title":"Progressive joint modeling in unsupervised single-channel overlapped speech recognition","volume":"26","author":"chen","year":"2017","journal-title":"Proc TASLP"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref12","first-page":"2797","article-title":"Serialized output training for end-to-end overlapped speech recognition","author":"kanda","year":"2020","journal-title":"Proc Inter-speech"},{"key":"ref13","article-title":"M2met: The icassp 2022 multi-channel multi-party meeting transcription challenge","author":"yu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178881"},{"key":"ref17","first-page":"7124","article-title":"Pyannote. audio: neural building blocks for speaker diarization","author":"bredin","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref3","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","author":"fiscus","year":"2007","journal-title":"Proc MTPH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref49","article-title":"Royalflush speaker diarization system for icassp 2022 multi-channel multi-party meeting transcription challenge","author":"tian","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746649"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413544"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1571"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"}],"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\/09746270.pdf?arnumber=9746270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T17:08:19Z","timestamp":1748365699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746270","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}