{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:23Z","timestamp":1775229803386,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1109\/asru.2007.4430116","type":"proceedings-article","created":{"date-parts":[[2008,1,16]],"date-time":"2008-01-16T20:07:44Z","timestamp":1200514064000},"page":"238-247","source":"Crossref","is-referenced-by-count":74,"title":["Recognition and understanding of meetings the AMI and AMIDA projects"],"prefix":"10.1109","author":[{"given":"Steve","family":"Renals","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Hain","sequence":"additional","affiliation":[]},{"given":"Herve","family":"Bourlard","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-366","article-title":"The segmentation of multi-channel meeting recordings for automatic speech recognition","author":"dines","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"35","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-434","article-title":"Dialogue act compression via pitch contour preservation","author":"murray","year":"2006","journal-title":"Proc INTERSPEECH '06"},{"key":"17","article-title":"The ISL meeting corpus: The impact of meeting type on speech style","author":"burger","year":"2002","journal-title":"Proc ICSLP"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1145\/1056808.1057082"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-543","article-title":"Transcription of conference room meetings: An investigation","author":"hain","year":"2005","journal-title":"Proc Interspeech '05"},{"key":"33","article-title":"Using audio, visual, and lexical features in a multi-modal virtual meeting director","author":"al-hames","year":"0","journal-title":"Proc MLMI '06 2006 AMI-164"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075167"},{"key":"16","article-title":"The nist meeting room pilot corpus","author":"garofolo","year":"2004","journal-title":"Proc 1st Int Conf Language Resources and Evaluation"},{"key":"13","article-title":"Progress in meeting recognition: The ICSI-SRI-UW spring 2004 evaluation system","author":"stolcke","year":"2004","journal-title":"Proc NISTRT05 Workshop"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366923"},{"key":"37","year":"0"},{"key":"11","doi-asserted-by":"crossref","DOI":"10.1109\/TASL.2006.881678","article-title":"Audio-visual probabilistic tracking of multiple speakers in meetings","author":"gatica-perez","year":"2007","journal-title":"IEEE Trans on Audio Speech and Language Processing"},{"key":"12","first-page":"176","article-title":"A study on visual focus of attention recognition from head pose in a meeting room","author":"ba","year":"2006","journal-title":"Proc MLMI '06"},{"key":"21","article-title":"The 2005 AMI system for the transcription of speech in meetings","author":"hain","year":"2005","journal-title":"Proc NIST RT'05 Workshop"},{"key":"20","article-title":"Direct optimisation of a multi-layer perceptron for the estimation of cepstral mean and variance statistics","author":"dines","year":"2007","journal-title":"Proc Interspeech '07"},{"key":"22","year":"0"},{"key":"23","article-title":"The development of the AMI system for the transcription of speech in meetings","author":"hain","year":"2005","journal-title":"Proc MLMI'05"},{"key":"24","author":"povey","year":"2004","journal-title":"Discriminative training for large vocabulary speech recognition"},{"key":"25","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2003-572","article-title":"MMI-MAP and MPE-MAP for acoustic model adaptation","author":"povey","year":"2003","journal-title":"Proc Eurospeech'03"},{"key":"26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2007-122","article-title":"Application of CMLLR in narrow band wide band adapted systems","author":"karafiat","year":"2007","journal-title":"Proc Interspeech 2007"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660209"},{"key":"28","article-title":"The 2007 AMI(DA) system for meeting transcription","author":"hain","year":"2007","journal-title":"Proc NIST RT'O6 Workshop"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367181"},{"key":"3","article-title":"Viewing meetings captured by an omni-directional camera","author":"yong","year":"2001","journal-title":"ACM Transactions on Computer-Human Interaction"},{"key":"2","first-page":"107","article-title":"Audio meeting history tool: Interactive graphical user-support for virtual audio meetings","author":"roy","year":"1999","journal-title":"Proc ESCA Workshop on Accessing Information in Spoken Audio"},{"key":"10","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/11965152_33","article-title":"The ami speaker diarization system for nist rt06s meeting data","volume":"4299","author":"van leeuwen","year":"2007","journal-title":"Lecture Notes in Computer Science"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/93.486705"},{"key":"30","article-title":"Automatic topic segmentation and labeling in multiparty dialogue","author":"hsueh","year":"2006","journal-title":"Proc IEEE\/ACL SLT '06"},{"key":"7","doi-asserted-by":"crossref","DOI":"10.1007\/11677482_4","article-title":"VACE multimodal meeting corpus","author":"chen","year":"2006","journal-title":"Proc Workshop on Machine Learning for Multimodal Interaction (MLMI)"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202749"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220882"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940902"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1145\/1180995.1181047"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641111"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-006-9001-9"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"}],"event":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","location":"The Westin Miyako Kyoto","start":{"date-parts":[[2007,12,9]]},"end":{"date-parts":[[2007,12,13]]}},"container-title":["2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4430067\/4430068\/04430116.pdf?arnumber=4430116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T10:15:54Z","timestamp":1708510554000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4430116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru.2007.4430116","relation":{},"subject":[],"published":{"date-parts":[[2007]]}}}