{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T08:05:24Z","timestamp":1771488324236,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T00:00:00Z","timestamp":1762905600000},"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":[[2025,11,12]]},"DOI":"10.1109\/o-cocosda68185.2025.11385084","type":"proceedings-article","created":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:14:09Z","timestamp":1771449249000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Joining Diarization and Multi-Speaker Automatic Speech Recognition with Overlap Handling for Long Conversations"],"prefix":"10.1109","author":[{"given":"Myat Aye Aye","family":"Aung","sequence":"first","affiliation":[{"name":"University of Computer Studies,Faculty of Computer Science,Yangon,Myanmar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Win Pa","family":"Pa","sequence":"additional","affiliation":[{"name":"Naypyitaw State Polytechnic University,Faculty of Computing,Naypyitaw,Myanmar"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology,Division of Information Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition, Signals and Communication Technology","author":"Yu","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_14"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-2648"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2023-1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3366756"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref13","article-title":"Joint speaker diarization and asr using end-to-end neural speaker diarization and recognition","author":"Kanda","year":"2021","journal-title":"in Proc. INTERSPEECH"},{"key":"ref14","article-title":"An investigation into the interactions between speaker diarisation systems and automatic speech transcription","author":"Tranter","year":"2003","journal-title":"Tech. Rep. CUED\/FINFENG\/TR 464, Cambridge University Engineering Department"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_46"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-17"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Nvidia nemo toolkit","year":"2025","journal-title":"NVIDIA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref21","article-title":"Multi-scale modeling for speaker diarization with self-attentive end-to-end neural networks","author":"Yin","year":"2020","journal-title":"in Proc. INTERSPEECH, 2020, in Proc. Interspeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","article-title":"Robust speech recognition via largescale weak supervision","author":"Radford","year":"2023","journal-title":"2023, A. Radford et al., \u201cRobust Speech Recognition via Large-Scale Weak Supervision,\u201dOpenAI Whisper"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA60357.2023.10482947"}],"event":{"name":"2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Yogyakarta, Indonesia","start":{"date-parts":[[2025,11,12]]},"end":{"date-parts":[[2025,11,14]]}},"container-title":["2025 28th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11383559\/11384821\/11385084.pdf?arnumber=11385084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T07:04:35Z","timestamp":1771484675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11385084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda68185.2025.11385084","relation":{},"subject":[],"published":{"date-parts":[[2025,11,12]]}}}