{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:09:00Z","timestamp":1776881340407,"version":"3.51.2"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687974","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"296-303","source":"Crossref","is-referenced-by-count":9,"title":["A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio"],"prefix":"10.1109","author":[{"given":"Naoyuki","family":"Kanda","sequence":"first","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong","family":"Meng","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corp.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2723507"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3070817"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383600"},{"key":"ref31","first-page":"2797","article-title":"Serialized output training for end-to-end overlapped speech recognition","author":"kanda","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461580"},{"key":"ref36","first-page":"5220","article-title":"A study on data augmentation of reverberant speech for robust speech recognition","author":"tom","year":"0","journal-title":"Proc ICASSP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414432"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413471"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2988423"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003884"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054577"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1085"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref56","first-page":"803","article-title":"Multiple dimension Levenshtein edit distance calculations for evaluating automatic speech recognition systems during simultaneous speech","author":"fiscus","year":"0","journal-title":"Proc LREC"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref54","first-page":"6000","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"Proc of NIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref11","first-page":"6630","article-title":"Acoustic modeling for distant multi-talker speech recognition with single- and multi-channel branches","author":"fujita","year":"0","journal-title":"Proc ICASSP"},{"key":"ref40","first-page":"2616","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415062"},{"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":"10.21437\/Interspeech.2019-1126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003827"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref45","article-title":"Res2net: A new multi-scale backbone architecture","author":"gao","year":"2019","journal-title":"IEEE Trans on PAMI"},{"key":"ref48","article-title":"VoxSRC 2020: The second VoxCeleb speaker recognition challenge","author":"nagrani","year":"0","journal-title":"ArXiv Preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref42","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"ASRU"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687974.pdf?arnumber=9687974","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:18Z","timestamp":1652733738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687974\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687974","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}