{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T04:29:24Z","timestamp":1745987364607,"version":"3.28.0"},"reference-count":32,"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\/icassp49357.2023.10094955","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Augmenting Transformer-Transducer Based Speaker Change Detection with Token-Level Training Loss"],"prefix":"10.1109","author":[{"given":"Guanlong","family":"Zhao","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Lu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiling","family":"Huang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignacio Lopez","family":"Moreno","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0969-4765(17)30033-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"year":"0","key":"ref31","article-title":"Google’s privacy principles"},{"key":"ref30","article-title":"First DIHARD challenge evaluation plan","author":"ryant","year":"2018","journal-title":"Tech Rep"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053280"},{"year":"0","key":"ref32","article-title":"Artificial intelligence at Google: Our principles"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.831666"},{"key":"ref1","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the bayesian information criterion","volume":"8","author":"chen","year":"1998","journal-title":"Proc DARPA Broadcast News Transcription and Understanding Workshop"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"3537","DOI":"10.21437\/Interspeech.2017-639","article-title":"Optimizing expected word error rate via sampling for speech recognition","author":"shannon","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-548"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-411"},{"key":"ref24","first-page":"69","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","volume":"4","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref23","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":"ref26","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/11677482_3","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2006","journal-title":"Machine Learning for Multimodal Interaction"},{"key":"ref25","article-title":"CALLHOME Amer-ican English speech LDC97S42","author":"canavan","year":"1997","journal-title":"LDC Catalog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref22","first-page":"74","author":"jurafsky","year":"2008","journal-title":"Speech and Language Processing An Introduction to Natural Language Processing Computational Linguistics and Speech Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"year":"0","key":"ref28","article-title":"Kaldi ICSI data split"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3451894"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1750"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-65"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040626"},{"article-title":"Highly efficient real-time streaming and fully on-device speaker diarization with multi-stage clustering","year":"2022","author":"wang","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10094955.pdf?arnumber=10094955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:28Z","timestamp":1700506828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094955","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}