{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:12:34Z","timestamp":1776881554184,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10848915","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":5,"title":["Personal Voice Activity Detection With Ultra-Short Reference Speech"],"prefix":"10.1109","author":[{"given":"Longting","family":"Xu","sequence":"first","affiliation":[{"name":"College of Information Science and Technology, Donghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Donghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"Zhang","sequence":"additional","affiliation":[{"name":"AI Research Center, Midea Group (Shanghai) Co.,Ltd.,Shanghai,China,201702"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"AI Research Center, Midea Group (Shanghai) Co.,Ltd.,Shanghai,China,201702"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Yin","sequence":"additional","affiliation":[{"name":"AI Research Center, Midea Group (Shanghai) Co.,Ltd.,Shanghai,China,201702"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Gao","sequence":"additional","affiliation":[{"name":"AI Research Center, Midea Group (Shanghai) Co.,Ltd.,Shanghai,China,201702"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461921"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495611"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5772\/4740"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-62"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-856"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-731","volume-title":"Enrollment-less training for personalized voice activity detection","author":"Makishima","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094752"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.30420\/456164049"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096664"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054266"},{"key":"ref15","article-title":"A unified framework for low-latency speaker extraction in cocktail party environments","volume-title":"Interspeech","author":"Hao","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume-title":"Interspeech","author":"McAuliffe","year":"2017"},{"key":"ref20","volume-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7953152"},{"key":"ref22","volume-title":"Speech-brain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref23","volume-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10848915.pdf?arnumber=10848915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:23:11Z","timestamp":1738045391000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10848915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10848915","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}