{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:22:35Z","timestamp":1775229755612,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832215","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1224-1231","source":"Crossref","is-referenced-by-count":1,"title":["Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR"],"prefix":"10.1109","author":[{"given":"Weiqing","family":"Wang","sequence":"first","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Kunal","family":"Dhawan","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Taejin","family":"Park","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Krishna C.","family":"Puvvada","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Ivan","family":"Medennikov","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Somshubra","family":"Majumdar","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"He","family":"Huang","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Jagadeesh","family":"Balam","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28 492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2294"},{"key":"ref3","article-title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1194"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447957"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746225"},{"key":"ref11","article-title":"An Investigation into the Interactions between Speaker Diarisation Systems and Automatic Speech Transcription","author":"Tranter","year":"2003","journal-title":"CUED\/F-INFENG\/TR-464"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_46"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2012.6343426"},{"key":"ref14","first-page":"3","article-title":"Speaker Diarization from Speech Transcripts","volume-title":"Proc. ICSLP","author":"Canseco-Rodriguez"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1947"},{"key":"ref18","article-title":"The 4th CHiME Speech Separation and Recognition Challenge","author":"Vincent","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/chime.2020\u20139"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-305"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1943"},{"key":"ref26","first-page":"6256","article-title":"End-to-End Monaural MultiSpeaker ASR System without Pretraining","volume-title":"Proc. ICASSP","author":"Chang"},{"key":"ref27","first-page":"237","article-title":"MIMO-SPEECH: End-toend Multi-Channel Multi-Speaker Speech Recognition","volume-title":"Proc. ASRU","author":"Chang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.calcs-1.7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641127"},{"key":"ref34","first-page":"2790","article-title":"Parameter-Efficient Transfer Learning for NLP","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref35","first-page":"69","article-title":"The Fisher Corpus: A Resource for the Next Generations of Speech-to-text","volume-title":"Proc. LREC","author":"Cieri"},{"key":"ref36","article-title":"2000 NIST Speaker Recognition Evaluation","author":"Przybocki","year":"2001"},{"key":"ref37","first-page":"28","article-title":"The AMI Meeting corpus: A Preannouncement","volume-title":"International workshop on machine learning for multimodal interaction","author":"Carletta"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446204"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref41","article-title":"Musan: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"},{"key":"ref42","article-title":"NeMo: A Toolkit for Building AI Applications Using Neural Modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv preprint arXiv:1909.09577"},{"key":"ref43","article-title":"Lhotse: A Speech Data Representation Library for the Modern Deep Learning Ecosystem","author":"\u017belasko","year":"2021","journal-title":"arXiv preprint arXiv:2110.12561"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832215.pdf?arnumber=10832215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:25Z","timestamp":1737398365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832215","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}