{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:53:56Z","timestamp":1775883236107,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Goodix Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3675922","type":"journal-article","created":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:10:34Z","timestamp":1773951034000},"page":"1471-1475","source":"Crossref","is-referenced-by-count":0,"title":["Bin-Wise Zone-Based Speech Presence Detection With Metric-Aligned DCF Optimization"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1055-0563","authenticated-orcid":false,"given":"Doyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0724-5871","authenticated-orcid":false,"given":"Sung Kyo","family":"Jung","sequence":"additional","affiliation":[{"name":"Audio BU, Goodix Technology, Leuven, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref4","first-page":"20925","article-title":"The cone of silence: Speech separation by localization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jenrungrot","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3225968"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MASS62177.2024.00024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713745"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11100"},{"key":"ref9","first-page":"24539","article-title":"Learning to separate voices by spatial regions","volume-title":"Proc. Mach. Learn. Res.","author":"Xu","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393713"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2769220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"issue":"2","key":"ref15","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1006\/csla.1996.0024","article-title":"A practical methodology for speech source localization with microphone arrays","volume":"11","author":"Brandstein","year":"1997","journal-title":"Comput. Speech Lang."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3248952"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3334101"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HSNMC.2002.1032545"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446581"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446945"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413580"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref28","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref29","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1085"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145307"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2001.969547"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832812"},{"issue":"11","key":"ref34","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1016\/j.specom.2006.09.003","article-title":"Binary and ratio time-frequency masks for robust speech recognition","volume":"48","author":"Srinivasan","year":"2006","journal-title":"Speech Commun."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2946.001.0001"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC61483.2024.10694623"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11447381.pdf?arnumber=11447381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:22:12Z","timestamp":1775881332000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11447381\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3675922","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}