{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T18:37:53Z","timestamp":1791311873527,"version":"4.3.1"},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1109\/icme.2003.1220921","type":"proceedings-article","created":{"date-parts":[[2004,6,22]],"date-time":"2004-06-22T16:27:43Z","timestamp":1087921663000},"page":"I-329","source":"Crossref","is-referenced-by-count":16,"title":["Audio-visual synchrony for detection of monologues in video archives"],"prefix":"10.1109","author":[{"given":"G.","family":"Iyengar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H.J.","family":"Nock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C.","family":"Neti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641070"},{"key":"2","article-title":"Look who's talking: Speaker detection using video and audio correlation","author":"cutler","year":"2000","journal-title":"Proc ICME"},{"key":"10","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2002.1005673","article-title":"Robust speech recognition in noisy environments: The IBM spine-2 evaluation system","author":"kingsbury","year":"2002","journal-title":"Proc ICASSP"},{"key":"1","year":"0","journal-title":"Text Retrieval Conference (Tree) Video Track"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2002.5745560","article-title":"Informative sub- spaces for audiovisual processing: High-level function from low-level fusion","author":"fisher","year":"2002","journal-title":"Proc ICASSP"},{"key":"6","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher","year":"2001","journal-title":"Proc NIPS"},{"key":"5","article-title":"Using audio-visual synchrony to locate sounds","author":"hershey","year":"1999","journal-title":"Proc NIPS"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.1999.793814"},{"key":"9","article-title":"Audio-visual speech recognition","author":"neti","year":"2000","journal-title":"CLSP Summer Workshop Tech Rep WSOOAVSR"},{"key":"8","article-title":"Facesync: Alinearop- erator for measuring synchronization of video facial images and audio tracks","author":"slaney","year":"2001","journal-title":"Proc NIPS"},{"key":"11","article-title":"Speaker, environment and channel change detection and clustering via the bayesian information criterion","author":"chen","year":"1998","journal-title":"Intl Conf on Acoust Sp AndSig Proc"}],"event":{"name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","location":"Baltimore, MD, USA","start":{"date-parts":[[2003,7,9]]},"end":{"date-parts":[[2003,7,9]]}},"container-title":["2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8655\/27433\/01220921.pdf?arnumber=1220921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,16]],"date-time":"2017-06-16T04:15:51Z","timestamp":1497586551000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1220921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/icme.2003.1220921","relation":{},"subject":[],"published":{"date-parts":[[2003]]}}}