{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:50:04Z","timestamp":1776887404219,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889446","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["Mamba-based Segmentation Model for Speaker Diarization"],"prefix":"10.1109","author":[{"given":"Alexis","family":"Plaquet","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naohiro","family":"Tawara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shota","family":"Horiguchi","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Ando","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-105"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414333"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3366756"},{"key":"ref7","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref8","first-page":"10041","article-title":"Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality","volume-title":"Proc. ICML","author":"Dao"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-205"},{"key":"ref10","article-title":"pyannote.audio speaker diarization pipeline at VoxSRC 2023","author":"Baroudi","year":"2023","journal-title":"The VoxCeleb Speaker Recognition Challenge"},{"key":"ref11","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"},{"key":"ref12","article-title":"SPMamba: State-space model is all you need in speech separation","author":"Li","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888514"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3483009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832304"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1274"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-628"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096626"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10466"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref28","article-title":"The AMI meetings corpus","volume-title":"Proc. Symposium on Annotating and Measuring Meeting Behavior","author":"Carletta"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1208"},{"key":"ref36","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-962"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-668"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2024-17"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889446.pdf?arnumber=10889446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:30Z","timestamp":1774416270000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889446","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}