{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:17Z","timestamp":1775200277943,"version":"3.50.1"},"reference-count":59,"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\/asru65441.2025.11434778","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?"],"prefix":"10.1109","author":[{"given":"Shota","family":"Horiguchi","sequence":"first","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Naohiro","family":"Tawara","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Takanori","family":"Ashihara","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Atsushi","family":"Ando","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]}],"member":"263","reference":[{"key":"ref1","first-page":"35","article-title":"Front-end processing for the CHiME-5 dinner party scenario","volume-title":"Proc. CHiME-5","author":"Boeddeker"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101841"},{"key":"ref5","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024","journal-title":"arXiv:2410.00037"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1602"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3162080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095185"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-668"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10451"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889475"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1050"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-10"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3350887"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10466"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1768"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2800"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref35","article-title":"Guidelines for AMI speech transcriptions","author":"Moore","year":"2005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-454"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447653"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-14"},{"key":"ref40","first-page":"2","article-title":"The HTK hidden Markov model toolkit: Design and philosophy","volume":"2","author":"Young","year":"1994","journal-title":"Ltd"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-429"},{"key":"ref43","article-title":"English MFA acoustic model v3.1.0","author":"McAuliffe","year":"2024"},{"key":"ref44","article-title":"English (US) MFA dictionary v3.1.0","author":"McAuliffe","year":"2024"},{"key":"ref45","article-title":"English (US) MFA G2P model v3.0.0","author":"McAuliffe","year":"2023"},{"key":"ref46","article-title":"Mandarin MFA acoustic model v3.0.0","author":"McAuliffe","year":"2024"},{"key":"ref47","article-title":"Mandarin (China) MFA dictionary v3.0.0","author":"McAuliffe","year":"2024"},{"key":"ref48","article-title":"Mandarin (China) MFA G2P model v3.0.0","author":"McAuliffe","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2116"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref53","article-title":"The 2009 (RT-09) rich transcription meeting recognition evaluation plan"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688044"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-923"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746074"},{"key":"ref58","first-page":"13","article-title":"The USTC-NERCSLIP systems for the CHiME-7 DASR challenge","volume-title":"Proc. CHiME","author":"Wang"},{"key":"ref59","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"Proc. ICML","author":"Radford"}],"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\/11434778.pdf?arnumber=11434778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:39Z","timestamp":1775192379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434778","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}