{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:43:51Z","timestamp":1760132631562},"reference-count":49,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383600","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"809-816","source":"Crossref","is-referenced-by-count":21,"title":["Investigation of End-to-End Speaker-Attributed ASR for Continuous Multi-Talker Recordings"],"prefix":"10.1109","author":[{"given":"Naoyuki","family":"Kanda","sequence":"first","affiliation":[]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.2799929"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref31","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref36","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref1","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","author":"fiscus","year":"2007","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9054577","article-title":"Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system","author":"kinoshita","year":"2020"},{"key":"ref26","first-page":"396","article-title":"Joint speech recognition and speaker diarization via sequence transduction","author":"elshafey","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1947"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref11","article-title":"The STC system for the CHiME-6 challenge","author":"medennikov","year":"2020","journal-title":"CHiME 2020 Workshop on Speech Processing in Everyday Environments"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682822"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682273"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref3","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"article-title":"First DIHARD challenge evaluation plan","year":"2018","author":"ryant","key":"ref6"},{"key":"ref5","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020","journal-title":"Proc CHiME 2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053760"},{"key":"ref45","article-title":"Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis","author":"raj","year":"2021","journal-title":"Proc SLT"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"article-title":"Layer normalization","year":"2016","author":"lei ba","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003826"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref43","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383600.pdf?arnumber=9383600","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:52Z","timestamp":1622496652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383600\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383600","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}