{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T17:27:28Z","timestamp":1781198848067,"version":"3.54.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096626","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":114,"title":["Wespeaker: A Research and Production Oriented Speaker Embedding Learning Toolkit"],"prefix":"10.1109","author":[{"given":"Hongji","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengdong","family":"Liang","sequence":"additional","affiliation":[{"name":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Horizon Robotics,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Xiang","sequence":"additional","affiliation":[{"name":"AISpeech Ltd,Suzhou,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanlei","family":"Deng","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of AI, X-LANCE Lab,CSE Dept,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Voxsrc 2019: The first voxceleb speaker recognition challenge","author":"chung","year":"2019","journal-title":"arXiv preprint arXiv 1912 02522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref34","author":"team","year":"2021","journal-title":"Silero vad Pre-trained enterprise-grade voice activity detector (VAD) number detector and language classifier"},{"key":"ref15","article-title":"Voxsrc 2021: The third voxceleb speaker recognition challenge","author":"brown","year":"2022","journal-title":"arXiv preprint arXiv 2201 04583"},{"key":"ref14","article-title":"Voxsrc 2020: The second voxceleb speaker recognition challenge","author":"nagrani","year":"2020","journal-title":"2012 arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref30","author":"snyder","year":"2015","journal-title":"MUSAN A Music Speech and Noise Corpus"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414676"},{"key":"ref19","article-title":"The sjtu x-lance lab system for cnsrc 2022","author":"chen","year":"2022","journal-title":"arXiv preprint arXiv 2206 11699"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005703"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414600"},{"key":"ref25","article-title":"Ar-cface: Additive angular margin loss for deep face recognition","author":"deng","year":"2019","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref20","article-title":"Unified hypersphere embedding for speaker recognition","author":"hajibabaei","year":"2018","journal-title":"arXiv preprint arXiv 1807 08312"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref28","author":"makarov","year":"2022","journal-title":"Id R&D system description to vox-celeb speaker recognition challenge 2022"},{"key":"ref27","article-title":"The speakin system for voxceleb speaker recognition challange 2021","author":"zhao","year":"2021","journal-title":"arXiv preprint arXiv 2109 08742"},{"key":"ref29","first-page":"1567","article-title":"Analysis of score normalization in multilingual speaker recognition","author":"matejka","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv preprint arXiv 1603 04467"},{"key":"ref7","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Speechbrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021","journal-title":"arXiv preprint arXiv 2106 04427"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref3","article-title":"But system description to voxceleb speaker recognition challenge 2019","author":"zeinali","year":"2019","journal-title":"arXiv preprint arXiv 1910 12731"},{"key":"ref6","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref5","first-page":"12","article-title":"The htk book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096626.pdf?arnumber=10096626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T19:11:49Z","timestamp":1734635509000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096626","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}