{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T07:52:46Z","timestamp":1747813966470,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037846","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"502-506","source":"Crossref","is-referenced-by-count":4,"title":["TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Pang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Gaosheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Transsion Holding Limited"}]},{"given":"Xiaoyue","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Transsion Holding Limited"}]},{"given":"Yang","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenzhen Transsion Holding Limited"}]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2016.7919005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413832"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-566"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-516"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383602"},{"key":"ref11","article-title":"The Bytedance speaker diarization system for the voxceleb speaker recognition challenge 2021","author":"Wang","year":"2021","journal-title":"INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2019.2961071"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref14","article-title":"The dku-dukeece-lenovo system for the diarization task of the 2021 voxceleb speaker recognition challenge","author":"Wang","year":"2021","journal-title":"INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref17","article-title":"A report on sound event detection with different binaural features","volume-title":"arXiv preprint arXiv:1710.02997","author":"Adavanne","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref21","article-title":"Voxsrc 2021: The third voxceleb speaker recognition challenge","author":"Brown","year":"2022","journal-title":"arXiv preprint arXiv:2201.04583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038258"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383490"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/widm.53"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"issue":"CONF","key":"ref29","article-title":"The kaldi speech recognition toolkit","volume-title":"ASRU","author":"Povey"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref32","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020","journal-title":"arXiv preprint arXiv:2006.01796"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref38","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint arXiv:1510.08484"},{"issue":"2.4","key":"ref39","first-page":"1","article-title":"Room impulse response generator","volume-title":"Technische Universiteit Eindhoven, Tech. Rep","volume":"2","author":"Habets","year":"2006"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383523"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037846.pdf?arnumber=10037846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:56:43Z","timestamp":1707832603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037846","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}