{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T04:45:43Z","timestamp":1729658743572,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icme.2004.1394602","type":"proceedings-article","created":{"date-parts":[[2005,3,21]],"date-time":"2005-03-21T20:07:39Z","timestamp":1111435659000},"page":"1787-1790","source":"Crossref","is-referenced-by-count":7,"title":["A multi-stream audio-video large-vocabulary Mandarin Chinese speech database"],"prefix":"10.1109","author":[{"family":"Luhong Liangi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Yu Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Feiyue Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.V.","family":"Nefian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2002.1179960"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1117\/12.453091"},{"journal-title":"The CMU pose illumination and expression (PIE) database of human faces","year":"0","author":"sim","key":"11"},{"journal-title":"Optimum Sensor Placement for Microphone Arrays","year":"1998","author":"rabinkin","key":"12"},{"key":"3","first-page":"7\/1","article-title":"design issues for a digital audio-visual integrated database","author":"chibelushi","year":"1996","journal-title":"IEE Colloquium on Integrated Audio-Visual Processing for Recognition Synthesis and Communication (Ref No 1996\/213)"},{"key":"2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1109\/79.911195","article-title":"Audiovisual speech processing","volume":"18","author":"chen","year":"2001","journal-title":"Signal Processing Magazine"},{"key":"1","article-title":"Audio-visual speech recognition","author":"neti","year":"2000","journal-title":"Final Workshop 2000 Report"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1038171"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1006168"},{"key":"6","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.2002-123","article-title":"Audio-visual continuous speech recognition using a coupled HMM","author":"liu","year":"2002","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP 02)"},{"key":"5","article-title":"Evaluation protocol for the XM2FDB database","author":"luettin","year":"1998","journal-title":"IDIAP Communication 98-05"},{"key":"4","first-page":"65","article-title":"Speaker independent audio-visual database for bimodal ASR","author":"potamianos","year":"1997","journal-title":"Proc of the European Tutorial and Research Workshop on Audio-visual Speech Processing"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674412"},{"key":"8","first-page":"1","article-title":"A survey on Chinese speech recognition","volume":"6","author":"fu","year":"1996","journal-title":"Communications of COLIPS"}],"event":{"name":"2004 IEEE International Conference on Multimedia and Expo (ICME)","acronym":"ICME-04","location":"Taipei, Taiwan"},"container-title":["2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9605\/30346\/01394602.pdf?arnumber=1394602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:00:29Z","timestamp":1706068829000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1394602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icme.2004.1394602","relation":{},"subject":[]}}