{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T20:41:36Z","timestamp":1694637696562},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2010,8,1]],"date-time":"2010-08-01T00:00:00Z","timestamp":1280620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2010,8]]},"DOI":"10.1109\/tasl.2009.2033955","type":"journal-article","created":{"date-parts":[[2009,10,8]],"date-time":"2009-10-08T19:23:00Z","timestamp":1255029780000},"page":"1354-1365","source":"Crossref","is-referenced-by-count":1,"title":["Speech Activity Detection for Multi-Party Conversation Analyses Based on Likelihood Ratio Test on Spatial Magnitude"],"prefix":"10.1109","volume":"18","author":[{"given":"K","family":"Ishizuka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S","family":"Araki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.876340"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198906"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(87)90015-5"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/89.985548"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855842"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.874403"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.855551"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/97.957270"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661205"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545036"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/89.294354"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e89-d.3.1050"},{"key":"ref27","year":"2001","journal-title":"Digital Cellular Telecommunications System (Phase 2+) Universal Mobile Telecommunications System (UMTS) Mandatory Speech Codec Speech Processing Functions Adaptive Multi-Rate (AMR) Speech Codec Voice Activity Detector (VAD)"},{"key":"ref64","first-page":"365","article-title":"a voice activity detector employing soft decision based noise spectrum adaptation","volume":"1","author":"sohn","year":"1998","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/89.928915"},{"key":"ref29","year":"2003","journal-title":"Speech Processing Transmission and Quality Aspects (STQ) Distributed Speech Recognition Extended Advanced Front-End Feature Extraction Algorithm Compression Algorithms Back-End Speech Reconstruction Algorithm"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1647314.1647327"},{"key":"ref2","article-title":"chil: computers in the human interaction loop","author":"waibel","year":"2004","journal-title":"5th Int Workshop Image Anal Multimedia Interactive Services"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415174"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(89)90067-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.1914118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163394"},{"key":"ref23","first-page":"2925","article-title":"filtering the unknown: speech activity detection in heterogeneous video collections","author":"huijbregts","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref26","year":"1996","journal-title":"A Silence Compression Scheme for G 729 Optimized for Terminals Conforming to Recommendation V 70"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00056-G"},{"key":"ref50","first-page":"501","article-title":"use of a csp-based voice activity detector for distant-talking asr","author":"armani","year":"2003","journal-title":"Proc INTERSPEECH"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_40"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/72.761727"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1171927"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/78.476440"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref54","first-page":"2194","article-title":"speaker diarization for multiple distant microphone meetings: mixing acoustic features and inter-channel time differences","author":"pardo","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_23"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1452392.1452446"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e91-d.3.467"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_35"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_47"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1007\/978-3-540-68585-2_44","volume":"lncs 4625","author":"van leeuwen","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_46"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_50"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_29"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940811"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940902"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202749"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1330588.1330595"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322210"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/27616"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.21437\/Interspeech.2008-451","article-title":"multi-modal recording, analysis and indexing of poster sessions","author":"kawahara","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/89.622576"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/89.568735"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7278"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415647"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.1781622"},{"key":"ref44","first-page":"2802","article-title":"voice activity detection with array signal processing in the wavelet domain","volume":"e86 a","author":"hioka","year":"2003","journal-title":"IEICE Trans Fundamentals"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/89.902284"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/5508665\/05280323.pdf?arnumber=5280323","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T01:05:52Z","timestamp":1634000752000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5280323\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,8]]},"references-count":67,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2009.2033955","relation":{},"ISSN":["1558-7916"],"issn-type":[{"value":"1558-7916","type":"print"}],"subject":[],"published":{"date-parts":[[2010,8]]}}}