{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:04:37Z","timestamp":1760954677592,"version":"3.28.0"},"reference-count":6,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icassp.2004.1326121","type":"proceedings-article","created":{"date-parts":[[2004,9,28]],"date-time":"2004-09-28T13:50:22Z","timestamp":1096379422000},"page":"I-857-60","source":"Crossref","is-referenced-by-count":10,"title":["A stream-weight optimization method for audio-visual speech recognition using multi-stream HMMs"],"prefix":"10.1109","volume":"1","author":[{"given":"S.","family":"Tamura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K.","family":"Iwano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Furui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","first-page":"1023","article-title":"Audio-visual speech recognition using MCE-based HMMs and model-dependent stream weights","volume":"2","author":"miyajima","year":"2000","journal-title":"Proc ICSLP2000"},{"key":"2","first-page":"65","article-title":"Speaker independent audio-visual database for bimodal ASR","author":"potamianos","year":"1997","journal-title":"Proc AVSP'97"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"6","first-page":"117","article-title":"Audio-visual speech recognition using lip movement extracted from side-face images","author":"yoshinaga","year":"2003","journal-title":"Proc AVSP2003"},{"key":"5","first-page":"2","article-title":"A robust multi-modal speech recognition method using optical-flow analysis","author":"tamura","year":"2002","journal-title":"Proc IDS02"},{"key":"4","first-page":"20","article-title":"Stream weight optimization of speech and lip image sequence for audio-visual speech recognition","volume":"3","author":"nakamura","year":"2000","journal-title":"Proc ICSLP2000"}],"event":{"name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","acronym":"ICASSP-04","location":"Montreal, Que., Canada"},"container-title":["2004 IEEE International Conference on Acoustics, Speech, and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9248\/29343\/01326121.pdf?arnumber=1326121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,14]],"date-time":"2017-03-14T17:05:16Z","timestamp":1489511116000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1326121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":6,"URL":"https:\/\/doi.org\/10.1109\/icassp.2004.1326121","relation":{},"subject":[]}}