{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:54:32Z","timestamp":1753602872358},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389736","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers"],"prefix":"10.1109","author":[{"given":"Guru Prakash","family":"Arumugam","sequence":"first","affiliation":[{"name":"Google LLC, Mountain View,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo-Yiin","family":"Chang","sequence":"additional","affiliation":[{"name":"Google LLC, Mountain View,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N. Sainath Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google LLC, Mountain View,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC, Mountain View,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaan","family":"Bijwadia","sequence":"additional","affiliation":[{"name":"Google LLC, Mountain View,CA,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"in International Conference on Machine Learning","author":"Graves"},{"key":"ref2","article-title":"SpeechStew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref8","article-title":"Input length matters: Improving RNN-T and MWER training for long-form telephony speech recognition","author":"Lu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1107"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1643"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022818"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383518"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref17","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"5329","article-title":"Xvectors: Robust DNN embeddings for speaker recognition","volume-title":"in Proc. ICASSP","author":"Snyder"},{"key":"ref19","article-title":"Version control of speaker recognition systems","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"article-title":"Speaker diarization: A journey from unsupervised to supervised approaches","volume-title":"Odyssey: The Speaker and Language Recognition Workshop","author":"Zhang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383600"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094955"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461478"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687942"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747879"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413803"},{"key":"ref39","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"Shen","year":"2019","journal-title":"arXiv preprint"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389736.pdf?arnumber=10389736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:47:13Z","timestamp":1706028433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389736\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389736","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}