{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:51:45Z","timestamp":1776887505203,"version":"3.51.2"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434654","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder"],"prefix":"10.1109","author":[{"given":"Muhammad","family":"Shakeel","sequence":"first","affiliation":[{"name":"Honda Research Institute Japan,Japan"}]},{"given":"Yui","family":"Sudo","sequence":"additional","affiliation":[{"name":"Honda Research Institute Japan,Japan"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Chyi-Jiunn","family":"Lin","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383556"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053426"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3350887"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447957"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-253"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref24","first-page":"91","article-title":"All-neural online source separation, counting, and diarization for meeting analysis","volume-title":"Proc. ICASSP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1137"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-15"},{"key":"ref30","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS, ser. NIPS \u201820","author":"Baevski"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","volume":"202","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.549"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1194"},{"key":"ref37","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053461"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref41","article-title":"The Hitachi-JHU DIHARD III System: Competitive end-to-end neural diarization and x-vector clustering systems combined by dover-lap","author":"Horiguchi","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3070817"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-101"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-971"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s00224-021-10066-5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530324"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434654.pdf?arnumber=11434654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:45Z","timestamp":1775192265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434654","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}