{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T18:40:01Z","timestamp":1739731201871,"version":"3.37.1"},"reference-count":78,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1109\/asru.2009.5373493","type":"proceedings-article","created":{"date-parts":[[2010,1,13]],"date-time":"2010-01-13T20:40:58Z","timestamp":1263415258000},"page":"1-10","source":"Crossref","is-referenced-by-count":4,"title":["Generalization problem in ASR acoustic model training and adaptation"],"prefix":"10.1109","author":[{"given":"Sadaoki","family":"Furui","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref73","article-title":"Large scale discriminative training for speech recognition","author":"woodland","year":"2000","journal-title":"Proc ITRW ASR"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2007.09.001"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162929"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479787"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518599"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479688"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.03.002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.463"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.901300"},{"key":"ref38","first-page":"2","article-title":"Recent advances in discriminative training for speech recognition","author":"mcdermott","year":"2009","journal-title":"Proc Spring Meeting"},{"article-title":"Speech recognition with dynamic Bayesian networks","year":"1998","author":"zweig","key":"ref78"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541105"},{"key":"ref32","first-page":"27","article-title":"Adaptation and compensation for speech recognition - learning from extra data to improve robustness","author":"lee","year":"2001","journal-title":"Proc Int Workshop Hands-Free Speech Communication"},{"key":"ref31","first-page":"1771","article-title":"Eigenvoices for speaker adaptation","author":"kuhn","year":"1998","journal-title":"Proc ICSLP"},{"key":"ref30","first-page":"1375","article-title":"Tree-structured speaker clustering for speaker-independent continuous speech recognition","author":"kosaka","year":"1994","journal-title":"Proc ICSLP"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1997.0036"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"81","DOI":"10.21437\/Eurospeech.1995-20","article-title":"A study of speaker adaptation based on minimum classification error training","author":"matsui","year":"1995","journal-title":"Proc EUROSPEECH"},{"key":"ref35","article-title":"Speech recognition system robust to noise and speaking styles","author":"matsuda","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318477"},{"key":"ref62","first-page":"1705","article-title":"Spontaneous speech recognition using a massively parallel decoder","author":"shinozaki","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"973","DOI":"10.21437\/Eurospeech.2003-336","article-title":"Time adjustable mixture weights for speaking rate fluctuation","author":"shinozaki","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref63","first-page":"4377","article-title":"Unsupervised cross-validation adaptation algorithms for improved adaptation performance","author":"shinozaki","year":"2009","journal-title":"Proc IEEE ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/78.175747"},{"key":"ref64","first-page":"1","article-title":"Unsupervised cross-validation and aggregated adaptations for improved speech recognition","author":"shinozaki","year":"2009","journal-title":"IPSJ SIG Technical Report 2009-SLP-75"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref65","first-page":"87","article-title":"Speaker adaptations algorithms for segment vocoder","author":"shiraki","year":"1987","journal-title":"Transactions of the Comittee on Speech Research"},{"key":"ref66","first-page":"147","article-title":"Hidden Markov model adaptation using maximum a posteriori liner regression","author":"siohan","year":"1999","journal-title":"Proc Workshop on Robust Methods for Speech Recognition in Adverse Conditions"},{"key":"ref29","article-title":"Hidden factor dynamic Bayesian networks for speech recognition","author":"korkmazsky","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref67","article-title":"Structural maximum a posteriori linear regression for fast HMM adaptation","author":"siohan","year":"2000","journal-title":"Proc ISCA ITRW ASR2000 Workshop"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(00)00052-2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479789"},{"key":"ref2","first-page":"3","article-title":"Impact of variabilities on speech recognition","author":"benzeghiba","year":"2006","journal-title":"Proc Specom"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607807"},{"key":"ref20","article-title":"Acoustic factorization","author":"gales","year":"2001","journal-title":"Proc ASRU 2001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1996.0013"},{"key":"ref24","first-page":"2007","article-title":"Discriminative learning in speech recognition","author":"he","year":"2007","journal-title":"Technical Report MSR-TR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/89.279278"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/89.701369","article-title":"On-line adaptive learning of the correlated continuous-density hidden Markov model for speech recognition","volume":"6","author":"huo","year":"1998","journal-title":"IEEE Trans Speech Audio Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390205"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960595"},{"key":"ref51","article-title":"Environmental robustness in automatic speech recognition","author":"rose","year":"2004","journal-title":"Proc COST278 and ISCA Workshop on Robustness Issues in Conversational Interaction"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543221"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.21437\/Eurospeech.1995-286","article-title":"Speaker adaptation with autonomous control using tree structure","author":"shinoda","year":"1995","journal-title":"Proc EUROSPEECH"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/89.906001"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150473"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"920","DOI":"10.21437\/Interspeech.2008-108","article-title":"Penalty function maximization for large margin HMM training","author":"saon","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596063"},{"key":"ref53","first-page":"67","article-title":"Analytic methods for acoustic model adaptation: a review","author":"sagayama","year":"2001","journal-title":"Proc ISCA Workshop"},{"key":"ref52","first-page":"1","article-title":"Factor analysed hidden Markov models","author":"rosti","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163393"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/29.45538"},{"key":"ref40","first-page":"725","article-title":"Speaking-rate dependent decoding and adaptation for spontaneous lecture speech recognition","author":"nanjo","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref12","first-page":"1","article-title":"50 years of progress in speech and speaker recognition","author":"furui","year":"2005","journal-title":"Proc Specom"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.366"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-1","article-title":"Selected topics from 40 years of research on speech and speaker recognition","author":"furui","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/11551874_3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828628"},{"key":"ref17","article-title":"The generation and use of regression class trees for MLLR adaptation","author":"gales","year":"1996","journal-title":"CUED\/F-INFENG\/TR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref19","first-page":"1783","article-title":"Cluster adaptive training for speech recognition","author":"gales","year":"1998","journal-title":"Proc ICSLP"},{"key":"ref4","article-title":"Eigenspace-based maximum a posteriori linear regression for rapid speaker adaptation","volume":"3 2","author":"chen","year":"2001","journal-title":"Proc ICASSP"},{"key":"ref3","first-page":"2001","article-title":"Graphical models and automatic speech recognition","author":"bilmes","year":"2001","journal-title":"UW Technical Report"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.466659"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"211","DOI":"10.21437\/Eurospeech.1999-56","article-title":"Maximum a posteriori linear regression for hidden Markov model adaptation","volume":"1","author":"chesta","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_33"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.506933"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TSA.1996.481449","article-title":"Signal bias removal by maximum likelihood estimation for robust telephone speech recognition","volume":"4","author":"rahim","year":"1996","journal-title":"IEEE Trans Speech Audio Process"},{"journal-title":"Pattern Classification","year":"2001","author":"duda","key":"ref9"},{"journal-title":"Discriminative training for large vocabulary speech recognition","year":"2003","author":"povey","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_30"},{"key":"ref48","first-page":"1047","article-title":"Experiments in speaker normalization and adaptation for large vocabulary speech recognition","volume":"2","author":"pye","year":"1997","journal-title":"Proc ICASSP"},{"key":"ref47","first-page":"105","article-title":"Minimum phone error and i-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-1367-0_3","article-title":"Maximum mutual information estimation of hidden Markov models","author":"normandin","year":"1996","journal-title":"Automatic Speech and Speaker Recognition"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1007\/BF03001909","article-title":"Eigenvoices: a compact representation of speakers in a model space","volume":"55","author":"nguyen","year":"2000","journal-title":"Annales des telecommunications"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.650313"},{"key":"ref43","first-page":"369","article-title":"Speaker adaptation based on transfer-vector-field smoothing with continuous mixture density HMMs","author":"ohkura","year":"1992","journal-title":"Proc ICSLP"}],"event":{"name":"Understanding (ASRU)","start":{"date-parts":[[2009,11,13]]},"location":"Moreno, Italy","end":{"date-parts":[[2009,12,17]]}},"container-title":["2009 IEEE Workshop on Automatic Speech Recognition & Understanding"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5357590\/5372876\/05373493.pdf?arnumber=5373493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T18:16:07Z","timestamp":1739729767000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5373493\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/asru.2009.5373493","relation":{},"subject":[],"published":{"date-parts":[[2009,12]]}}}