{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:32:01Z","timestamp":1779323521183,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446581","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11476-11480","source":"Crossref","is-referenced-by-count":11,"title":["AS-pVAD: A Frame-Wise Personalized Voice Activity Detection Network with Attentive Score Loss"],"prefix":"10.1109","author":[{"given":"Fenting","family":"Liu","sequence":"first","affiliation":[{"name":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feifei","family":"Xiong","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiya","family":"Hao","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kechenying","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science & Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Feng","sequence":"additional","affiliation":[{"name":"Alibaba Group,Hummingbird Audio Lab,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.1993.327987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/35.620527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/97.995824"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-527"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414470"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2018.8547084"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-820"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-856"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1602"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-731"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747765"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096411"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-677"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747772"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023039"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","first-page":"146","article-title":"Investigating rnn-based speech enhancement methods for noise-robust text-tospeech","volume-title":"9th ISCA Speech Synthesis Workshop","author":"Valentini-Botinhao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097247"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2028"},{"key":"ref32","first-page":"2573","article-title":"Creating HAVIC: Heterogeneous audio visual internet collection","volume-title":"8-th International Conference on Language Resources and Evaluation (LREC)","author":"Strassel"},{"key":"ref33","first-page":"35","article-title":"Speech database development: TIMIT and beyond","volume":"2","author":"Zue","year":"1989","journal-title":"Speech Input\/Output Assessment and Speech Databases"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577502"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2843537"},{"issue":"2605","key":"ref37","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446581.pdf?arnumber=10446581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:21:43Z","timestamp":1722576103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446581","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}