{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T21:13:15Z","timestamp":1760044395370,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447263","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11801-11805","source":"Crossref","is-referenced-by-count":2,"title":["USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models"],"prefix":"10.1109","author":[{"given":"Guanlong","family":"Zhao","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Pelecanos","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hank","family":"Liao","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":"Han","family":"Lu","sequence":"additional","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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.831666"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746531"},{"article-title":"Highly efficient real-time streaming and fully on-device speaker diarization with multistage clustering","year":"2022","author":"Wang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3040626"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3451894"},{"key":"ref6","article-title":"Multimodal few-shot learning with frozen language models","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1750"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053280"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0969-4765(17)30033-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094955"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096361"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-703"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3201445"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094972"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-777"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref22","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref24","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. ICML","author":"Chiu"},{"key":"ref25","article-title":"Google\u2019s privacy principles"},{"key":"ref26","article-title":"Artificial intelligence at Google: Our principles"},{"article-title":"Input length matters: Improving RNN-T and MWER training for long-form telephony speech recognition","year":"2021","author":"Lu","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref29","article-title":"CALLHOME American English speech LDC97S42","volume-title":"LDC Catalog","author":"Canavan","year":"1997"},{"key":"ref30","article-title":"First DIHARD challenge evaluation plan","volume-title":"Tech. Rep.","author":"Ryant","year":"2018"},{"key":"ref31","first-page":"69","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","volume-title":"LREC","volume":"4","author":"Cieri"},{"key":"ref32","article-title":"Kaldi ICSI data split"},{"key":"ref33","first-page":"4596","article-title":"Adafactor: Adaptive learning rates with sublinear memory cost","volume-title":"Proc. ICML","author":"Shazeer"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"key":"ref36","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref37","article-title":"Cloud tensor processing units (TPUs)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096273"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447263.pdf?arnumber=10447263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:41:00Z","timestamp":1722573660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447263","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}