{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:47:23Z","timestamp":1747201643487},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414432","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6763-6767","source":"Crossref","is-referenced-by-count":4,"title":["Hypothesis Stitcher for End-to-End Speaker-Attributed ASR on Long-Form Multi-Talker Recordings"],"prefix":"10.1109","author":[{"given":"Xuankai","family":"Chang","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,USA"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004009"},{"article-title":"Investigation of end-to-end speaker-attributed asr for continuous multi-talker recordings","year":"2020","author":"kanda","key":"ref13"},{"key":"ref14","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref3","first-page":"28","author":"carletta","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref8","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":"ref7","article-title":"CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings","author":"watanabe","year":"2020","journal-title":"Proc CHiME 2020"},{"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":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"article-title":"RNN-T models fail to generalize to out-of-domain audio: Causes and solutions","year":"2020","author":"chiu","key":"ref20"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414432.pdf?arnumber=9414432","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:18:26Z","timestamp":1659485906000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414432\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414432","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}