{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T10:43:39Z","timestamp":1742381019233,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746116","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8087-8091","source":"Crossref","is-referenced-by-count":5,"title":["A Multitask Learning Framework for Speaker Change Detection with Content Information from Unsupervised Speech Decomposition"],"prefix":"10.1109","author":[{"given":"Hang","family":"Su","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Dang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minglei","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Cloud,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2017.7953192"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2017.7953194"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2017-1650"},{"key":"ref13","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the bayesian information criterion","volume":"8","author":"chen","year":"1998","journal-title":"Proc DARPA Broadcast News Transcription and Understanding Workshop"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.csl.2004.05.008"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.1991.150477"},{"key":"ref16","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","volume":"1997","author":"siegler","year":"1997","journal-title":"Proc DARPA Speech Recognition Workshop"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICASSP.2019.8683612"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICASSP.2015.7178806"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-319-43958-7_22"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-180","article-title":"Fast speaker change detection for broadcast news transcription and indexing","author":"liu","year":"1999","journal-title":"Sixth European Conference on Speech Communication and Technology"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 San Diego CA USA May 7-9 2015 Conference Track Proceedings"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP40776.2020.9053280"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1016\/j.csl.2005.08.002"},{"key":"ref5","article-title":"Speaker change detection using a new weighted distance measure","author":"kwon","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2015-106"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TASL.2006.878261"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2017.7953097"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2017.7953199"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref20","first-page":"649","article-title":"An approach to online speaker change point detection using DNNs and WF-STs","author":"mateju","year":"0"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/TASLP.2021.3067161"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2017-65"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref23","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref26","first-page":"28","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Int Workshop Mach Learn Multimodal Interact"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/CVPR.2015.7298682"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746116.pdf?arnumber=9746116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:24:06Z","timestamp":1727061846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746116","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}