{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:00:56Z","timestamp":1775199656783,"version":"3.50.1"},"reference-count":34,"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\/asru65441.2025.11434629","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":0,"title":["On the Use of Self-Supervised Representation Learning for Speaker Diarization and Separation"],"prefix":"10.1109","author":[{"given":"S\u00e9verin","family":"Baroudi","sequence":"first","affiliation":[{"name":"Université de Toulon, Aix Marseille Univ CNRS LIS,Toulon,France"}]},{"given":"Herv\u00e9","family":"Bredin","sequence":"additional","affiliation":[{"name":"IRIT \/ pyannote.ai,Toulouse,France"}]},{"given":"Joseph","family":"Razik","sequence":"additional","affiliation":[{"name":"Université de Toulon, Aix Marseille Univ CNRS LIS,Toulon,France"}]},{"given":"Ricard","family":"Marxer","sequence":"additional","affiliation":[{"name":"Université de Toulon, Aix Marseille Univ CNRS LIS,Toulon,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-962"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096876"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems, ser. NIPS\u201920.","author":"Baevski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"ref9","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref10","first-page":"5206","article-title":"Librispeech: An ASR corpus based on public domain audio books","volume-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Panayotov"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref15","article-title":"Tasnet: Surpassing ideal time-frequency masking for speech separation","volume":"abs\/1809.07454","year":"2018","journal-title":"CoRR"},{"key":"ref16","first-page":"46","article-title":"Dual-path rnn: Efficient long sequence modeling for time-domain single-channel speech separation","volume-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Luo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref18","article-title":"W2vbert: Combining contrastive learning and masked language modeling for self-supervised speech pre-training","volume":"abs\/2108.06209","author":"Chung","year":"2021","journal-title":"CoRR"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter","volume":"1","author":"Devlin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR)","author":"Baevski"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"issue":"1","key":"ref23","first-page":"3","article-title":"Announcing the ami meeting corpus","volume-title":"The ELRA Newsletter","volume":"11","author":"Carletta"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"issue":"333","key":"ref31","first-page":"1","article-title":"Open-source conversational ai with speechbrain 1.0","volume":"25","author":"Ravanelli","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref33","first-page":"3942","article-title":"Film: Visual reasoning with a general conditioning layer","volume-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18).","author":"Perez"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-17"}],"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\/11434629.pdf?arnumber=11434629","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:25Z","timestamp":1775192245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434629\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434629","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}