{"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":1775229758386,"version":"3.50.1"},"reference-count":27,"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\/icassp49357.2023.10094928","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Simulating Realistic Speech Overlaps Improves Multi-Talker ASR"],"prefix":"10.1109","author":[{"given":"Muqiao","family":"Yang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,PA,USA"}]},{"given":"Naoyuki","family":"Kanda","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Sunit","family":"Sivasankaran","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft,Redmond,WA,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3070817"},{"key":"ref12","first-page":"2797","article-title":"Serialized output training for end-to-end overlapped speech recognition","author":"kanda","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413471"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-169"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-102"},{"key":"ref16","article-title":"VarArray meets t-SOT: Advancing the state of the art of streaming distant conversational speech recognition","author":"kanda","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10451"},{"key":"ref24","first-page":"803","article-title":"Multiple dimension Levenshtein edit distance calculations for evaluating automatic speech recognition systems during simultaneous speech","author":"fiscus","year":"2006","journal-title":"Proc LREC"},{"key":"ref23","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref21","first-page":"28","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref9","first-page":"6256","article-title":"End-to-end monaural multi-speaker ASR system without pre-training","author":"chang","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref4","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":"\u00f6zg\u00fcr\u00e7etin","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"}],"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\/10094928.pdf?arnumber=10094928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:57:30Z","timestamp":1700488650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094928","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}