{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:21:21Z","timestamp":1776082881980,"version":"3.50.1"},"reference-count":54,"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\/icassp49660.2025.10888389","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":10,"title":["3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization"],"prefix":"10.1109","author":[{"given":"Yafeng","family":"Chen","sequence":"first","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Siqi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Luyao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Tinglong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Rongjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Chong","family":"Deng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Qian","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Shiliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Wen","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Speech Lab"}]},{"given":"Xihao","family":"Li","sequence":"additional","affiliation":[{"name":"University of North Carolina,Chapel Hill"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref5","article-title":"Disentangling Voice and Content with Self-Supervision for Speaker Recognition","volume-title":"NeurIPS 2023","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3240008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746270"},{"key":"ref9","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"ICML 2022","volume":"162","author":"Casanova"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888080"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747526"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022470"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3198315"},{"key":"ref14","article-title":"The Kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref16","article-title":"SpeechBrain: A generalpurpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414676"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096626"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.884"},{"key":"ref21","article-title":"Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation","author":"Cheng","year":"2023"},{"key":"ref22","article-title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","author":"Cheng","year":"2024"},{"key":"ref23","article-title":"3D-Speaker: A Large-Scale Multi-Device, MultiDistance, and Multi-Dialect Corpus for Speech Representation Disentanglement","author":"Zheng","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2938758"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1294"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-742"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096915"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890786"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1275"},{"key":"ref36","article-title":"PoNet: Pooling Network for Efficient Token Mixing in Long Sequences","volume-title":"ICLR 2022","author":"Tan"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3116"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10106"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746225"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_24"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00594"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1397"},{"key":"ref46","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume-title":"NAACL-HLT 2019","author":"Devlin"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0602-z"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746411"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101254"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_28"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"}],"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\/10888389.pdf?arnumber=10888389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:57Z","timestamp":1774416237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888389","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}