{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T01:38:08Z","timestamp":1792114688711,"version":"4.4.0"},"reference-count":201,"publisher":"Emerald","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,2,21]]},"abstract":"<jats:p>Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs.<\/jats:p>\n                  <jats:p>Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication.<\/jats:p>\n                  <jats:p>The aim of this review is first to present the core architecture of a HMM-based LVCSR system and then describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.<\/jats:p>","DOI":"10.1561\/2000000004","type":"journal-article","created":{"date-parts":[[2008,3,13]],"date-time":"2008-03-13T10:20:54Z","timestamp":1205403654000},"page":"195-304","source":"Crossref","is-referenced-by-count":485,"title":["The Application of Hidden Markov Models in Speech Recognition"],"prefix":"10.1108","volume":"1","author":[{"given":"Mark","family":"Gales","sequence":"first","affiliation":[{"name":"Cambridge University Engineering Department , Trumpington Street, Cambridge, CB2 1PZ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steve","family":"Young","sequence":"additional","affiliation":[{"name":"Cambridge University Engineering Department , Trumpington Street, Cambridge, CB2 1PZ,","place":["UK"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2008,2,21]]},"reference":[{"key":"2026040313315344400_ref001","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3122-7","volume-title":"Acoustical and Environmental Robustness in Automatic Speech Recognition","author":"Acero","year":"1993"},{"key":"2026040313315344400_ref002","volume-title":"Proceedings of ICSLP","author":"Acero","year":"2000"},{"key":"2026040313315344400_ref003","volume-title":"Proceedings of Interspeech","author":"Afify","year":"2005"},{"issue":"3","key":"2026040313315344400_ref004","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1006\/csla.1997.0031","article-title":"Combined Bayesian and predictive tech- niques for rapid speaker adaptation of continuous density hidden Markov mod- els,","volume":"11","author":"Ahadi","year":"1997","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref005","volume-title":"Proceedings of ICSLP","author":"Anastasakos","year":"1996"},{"key":"2026040313315344400_ref006","volume-title":"Using Observation Uncertainty for Robust Speech Recognition","author":"Arrowood","year":"2003"},{"key":"2026040313315344400_ref007","first-page":"49","volume-title":"Proceedings of ICASSP","author":"Aubert","year":"1995"},{"key":"2026040313315344400_ref008","volume-title":"Proceedings of ICSLP","author":"Axelrod","year":"2002"},{"key":"2026040313315344400_ref009","first-page":"49","volume-title":"Proceedings of ICASSP","author":"Bahl","year":"1986"},{"key":"2026040313315344400_ref010","first-page":"533","volume-title":"Proceedings of ICASSP","author":"Bahl","year":"1994"},{"issue":"1","key":"2026040313315344400_ref011","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TASSP.1975.1162650","article-title":"The Dragon system \u2014 An overview,","volume":"23","author":"Baker","year":"1975","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"2026040313315344400_ref012","doi-asserted-by":"crossref","first-page":"213","DOI":"10.21437\/Eurospeech.2001-76","volume-title":"Proceedings of Eurospeech","author":"Barker","year":"2001"},{"key":"2026040313315344400_ref013","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1090\/S0002-9904-1967-11751-8","article-title":"An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology,","volume":"73","author":"Baum","year":"1967","journal-title":"Bulletin of American Mathematical Society"},{"key":"2026040313315344400_ref014","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1214\/aoms\/1177697196","article-title":"A maximisation tech- nique occurring in the statistical analysis of probabilistic functions of Markov chains","volume":"41","author":"Baum","year":"1970","journal-title":"Annals of Mathematical Statistics"},{"key":"2026040313315344400_ref015","volume-title":"Proceedings of ASRU","author":"Beyerlein","year":"1997"},{"key":"2026040313315344400_ref016","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/S0885-2308(03)00010-X","article-title":"Buried Markov models: A graphical-modelling approach to automatic speech recognition,","volume":"17","author":"Bilmes","year":"2003","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref017","volume-title":"Math- ematical Foundations of Speech and Language: Processing Institute of Mathe- matical Analysis Volumes in Mathematics Series,","author":"Bilmes","year":"2003"},{"key":"2026040313315344400_ref018","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","article-title":"Suppression of acoustic noise in speech using spectral subtraction","volume":"27","author":"Boll","year":"1979","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"2026040313315344400_ref019","volume-title":"Proceedings of ICSLP","author":"Breslin","year":"2006"},{"key":"2026040313315344400_ref020","doi-asserted-by":"crossref","DOI":"10.21236\/ADA188529","volume-title":"The Acoustic-Modelling Problem in Automatic Speech Recogni- tion","author":"Brown","year":"1987"},{"issue":"4","key":"2026040313315344400_ref021","first-page":"467","article-title":"Class-based \ud835\udc41 -gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Computational Linguistics"},{"issue":"3","key":"2026040313315344400_ref022","doi-asserted-by":"crossref","first-page":"900","DOI":"10.1093\/ietisy\/e89-d.3.900","article-title":"Minimum Bayes risk estimation and decoding in large vocabulary continuous speech recognition","volume":"E89- D","author":"Byrne","year":"2006","journal-title":"IEICE Transactions on Information and Sys- tems: Special Issue on Statistical Modelling for Speech Recognition"},{"key":"2026040313315344400_ref023","volume-title":"Proceedings of ICASSP","author":"Chan","year":"2004"},{"key":"2026040313315344400_ref024","volume-title":"Proceedings of ICSLP","author":"Chen","year":"2000"},{"key":"2026040313315344400_ref025","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1006\/csla.1999.0128","article-title":"An empirical study of smoothing techniques for language modelling","volume":"13","author":"Chen","year":"1999","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref026","volume-title":"NIPS","author":"Chen","year":"2000"},{"key":"2026040313315344400_ref027","first-page":"1087","volume-title":"Proceedings of Eurospeech","author":"Chen","year":"1997"},{"key":"2026040313315344400_ref028","first-page":"1","volume-title":"Proceedings of ICASSP","author":"Chou","year":"1999"},{"key":"2026040313315344400_ref029","first-page":"652","volume-title":"Proceedings of ICASSP","author":"Chou","year":"1993"},{"key":"2026040313315344400_ref030","first-page":"1555","volume-title":"Proceedings of ICSLP","author":"Cooke","year":"1994"},{"key":"2026040313315344400_ref031","first-page":"863","volume-title":"Proceedings of ICASSP","author":"Cooke","year":"1997"},{"issue":"4","key":"2026040313315344400_ref032","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representa- tions for monosyllabic word recognition in continuously spoken sentences","volume":"28","author":"Davis","year":"1980","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"2026040313315344400_ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"Journal of the Royal Statistical Soci- ety Series B"},{"key":"2026040313315344400_ref034","first-page":"806","volume-title":"Proceedings of ICSLP","author":"Deng","year":"2000"},{"issue":"2","key":"2026040313315344400_ref035","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1109\/89.748122","article-title":"Maximum likelihood stochastic transfor- mation adaptation of hidden Markov models","volume":"7","author":"Diakoloukas","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref036","first-page":"765","volume-title":"Proceedings of ICASSP","author":"Digalakis","year":"1999"},{"key":"2026040313315344400_ref037","volume-title":"Proceedings of ICASSP","author":"Dimitrakakis","year":"2004"},{"key":"2026040313315344400_ref038","volume-title":"Proceedings of ICASSP","author":"Droppo","year":"2002"},{"key":"2026040313315344400_ref039","doi-asserted-by":"crossref","first-page":"217","DOI":"10.21437\/Eurospeech.2001-77","volume-title":"Proceedings of Eurospeech","author":"Droppo","year":"2001"},{"key":"2026040313315344400_ref040","volume-title":"Proceedings of ICASSP","author":"Evermann","year":"2004"},{"key":"2026040313315344400_ref041","first-page":"1655","volume-title":"Proceedings of ICASSP","author":"Evermann","year":"2000"},{"key":"2026040313315344400_ref042","volume-title":"Proceedings of Speech Transcription Workshop","author":"Evermann","year":"2000"},{"key":"2026040313315344400_ref043","first-page":"347","volume-title":"Proceedings of IEEE ASRU Workshop","author":"Fiscus","year":"1997"},{"key":"2026040313315344400_ref044","article-title":"Experiments with a new boosting algorithm","author":"Freund","year":"1996","journal-title":"Proceedings of the Thirteenth International Conference on Machine Learning"},{"key":"2026040313315344400_ref045","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision theoretic generalization of on-line learning and an application to boosting","author":"Freund","year":"1997","journal-title":"Journal of Computer and System Sciences"},{"key":"2026040313315344400_ref046","volume-title":"Introduction to Statistical Pattern Recognition","author":"Fukunaga","year":"1972"},{"key":"2026040313315344400_ref047","first-page":"52","volume-title":"IEEE Transactions ASSP","author":"Furui","year":"1986"},{"key":"2026040313315344400_ref048","volume-title":"Model-based Techniques for Noise Robust Speech Recognition","author":"Gales","year":"1995"},{"key":"2026040313315344400_ref049","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.21437\/Eurospeech.1997-547","volume-title":"Proceedings of Eurospeech","author":"Gales","year":"1997"},{"key":"2026040313315344400_ref050","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/csla.1998.0043","article-title":"Maximum likelihood linear transformations for HMM-based speech recognition,","volume":"12","author":"Gales","year":"1998","journal-title":"Computer Speech and Language"},{"issue":"3","key":"2026040313315344400_ref051","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1109\/89.759034","article-title":"Semi-tied covariance matrices for hidden Markov models","volume":"7","author":"Gales","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref052","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/89.848223","article-title":"Cluster adaptive training of hidden Markov models","volume":"8","author":"Gales","year":"2000","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"2","key":"2026040313315344400_ref053","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/89.985541","article-title":"Maximum likelihood multiple subspace projections for hidden Markov models","volume":"10","author":"Gales","year":"2002","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref054","author":"Gales","year":"2007","journal-title":"ITA Work- shop"},{"key":"2026040313315344400_ref055","volume-title":"Proceedings of ICASSP","author":"Gales","year":"2005"},{"issue":"5","key":"2026040313315344400_ref056","article-title":"Progress in the CU-HTK broadcast news transcription system","volume":"14","author":"Gales","year":"2006","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"2026040313315344400_ref057","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/0167-6393(93)90093-Z","article-title":"Cepstral parameter compensation for HMM recognition in noise,","volume":"12","author":"Gales","year":"1993","journal-title":"Speech Communication"},{"issue":"4","key":"2026040313315344400_ref058","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1006\/csla.1995.0014","article-title":"Robust speech recognition in additive and convolutional noise using parallel model combination","volume":"9","author":"Gales","year":"1995","journal-title":"Computer Speech and Language"},{"issue":"5","key":"2026040313315344400_ref059","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/89.536929","article-title":"Robust continuous speech recognition using parallel model combination","volume":"4","author":"Gales","year":"1996","journal-title":"IEEE Transactions on Speech and Audio Pro- cessing"},{"key":"2026040313315344400_ref060","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.21437\/Eurospeech.1997-553","volume-title":"Proceedings of EuroSpeech","author":"Gao","year":"1997"},{"issue":"2","key":"2026040313315344400_ref061","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/89.279278","article-title":"Maximum a posteriori estimation of multivariate Gaussian mixture observations of Markov chains","volume":"2","author":"Gauvain","year":"1994","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref062","first-page":"517","volume-title":"Pro- ceedings of ICASSP","author":"Godfrey","year":"1992"},{"key":"2026040313315344400_ref063","volume-title":"Proceedings of ICSLP","author":"Goel","year":"2000"},{"key":"2026040313315344400_ref064","first-page":"631","volume-title":"Proceedings of ICASSP","author":"Gopalakrishnan","year":"1989"},{"key":"2026040313315344400_ref065","volume-title":"Proceedings of ICASSP","author":"Gopinath","year":"1998"},{"key":"2026040313315344400_ref066","volume-title":"Pro- ceedings of ARPA Workshop on Spoken Language System Technology","author":"Gopinath","year":"1999"},{"key":"2026040313315344400_ref067","volume-title":"Proceedings of Interspeech","author":"Gunawardana","year":"2005"},{"key":"2026040313315344400_ref068","first-page":"13","volume-title":"Proceedings of ICASSP","author":"Haeb-Umbach","year":"1992"},{"key":"2026040313315344400_ref069","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/89.279287","article-title":"Improvements in time-synchronous beam search for 10000-word continuous speech recognition","volume":"2","author":"Haeb-Umbach","year":"1994","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref070","article-title":"Implicit pronunciation modelling in ASR,","author":"Hain","year":"2002","journal-title":"ISCA ITRW PMLA"},{"key":"2026040313315344400_ref071","first-page":"57","volume-title":"Pro- ceedings of ICASSP","author":"Hain","year":"1999"},{"issue":"4","key":"2026040313315344400_ref072","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2005.07.005","article-title":"Beyond ASR 1-best: Using word confusion networks in spoken language understanding","volume":"20","author":"Hakkani-Tur","year":"2006","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref073","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.21437\/Eurospeech.1997-542","article-title":"A comparison of novel techniques for instantaneous speaker adaptation,","author":"Hazen","year":"1997","journal-title":"Proceedings of Eurospeech"},{"issue":"4","key":"2026040313315344400_ref074","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","article-title":"Perceptual linear predictive (PLP) analysis of speech","volume":"87","author":"Hermansky","year":"1990","journal-title":"Jour- nal of Acoustical Society of America"},{"issue":"4","key":"2026040313315344400_ref075","article-title":"RASTA processing of speech,","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Trans- actions on Speech and Audio Processing"},{"key":"2026040313315344400_ref076","doi-asserted-by":"crossref","DOI":"10.1147\/rd.136.0675","article-title":"A fast sequential decoding algorithm using a stack","volume":"13","author":"Jelinek","year":"1969","journal-title":"IBM Journal on Research and Development"},{"issue":"4","key":"2026040313315344400_ref077","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/PROC.1976.10159","article-title":"Continuous speech recognition by statistical methods","volume":"64","author":"Jelinek","year":"1976","journal-title":"Proceed- ings of IEEE"},{"issue":"11","key":"2026040313315344400_ref078","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.1109\/PROC.1985.13343","article-title":"A discrete utterance recogniser","volume":"73","author":"Jelinek","year":"1985","journal-title":"Proceedings of IEEE"},{"issue":"5","key":"2026040313315344400_ref079","doi-asserted-by":"crossref","first-page":"1584","DOI":"10.1109\/TASL.2006.879805","article-title":"Large margin hidden Markov models for speech recognition","volume":"14","author":"Jiang","year":"2006","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"7","key":"2026040313315344400_ref080","first-page":"1213","article-title":"On the hidden Markov model and dynamic time warping for speech recognition \u2014 A unified view,","volume":"63","author":"Juang","year":"1984","journal-title":"AT and T Technical Journal"},{"issue":"6","key":"2026040313315344400_ref081","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1002\/j.1538-7305.1985.tb00273.x","article-title":"Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains,","volume":"64","author":"Juang","year":"1985","journal-title":"AT and T Technical Journal"},{"issue":"4","key":"2026040313315344400_ref082","article-title":"Discriminative learning for minimum error clas- sification","volume":"14","author":"Juang","year":"1992","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"2","key":"2026040313315344400_ref083","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1109\/TIT.1986.1057145","article-title":"Maximum likelihood esti- mation for multivariate mixture observations of Markov chains","volume":"32","author":"Juang","year":"1986","journal-title":"IEEE Trans- actions on Information Theory"},{"key":"2026040313315344400_ref084","volume-title":"Proceedings of ICSLP","author":"Kaiser","year":"2000"},{"key":"2026040313315344400_ref085","first-page":"400","volume-title":"IEEE Transactions on ASSP","author":"Katz","year":"1987"},{"key":"2026040313315344400_ref086","first-page":"2725","article-title":"Unsupervised training of a speech recognizer: Recent experiments,","author":"Kemp","year":"1999","journal-title":"Proceedings of EuroSpeech"},{"key":"2026040313315344400_ref087","first-page":"105","author":"Kim","year":"2003","journal-title":"Proceedings of IEEE ASRU Workshop"},{"key":"2026040313315344400_ref088","volume-title":"Proceedings of ICSLP","author":"Kim","year":"2004"},{"issue":"2","key":"2026040313315344400_ref089","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1049\/el:19710039","article-title":"Digital filtering using logarithmic arithmetic","volume":"7","author":"Kingsbury","year":"1971","journal-title":"Electronics Letters"},{"key":"2026040313315344400_ref090","doi-asserted-by":"crossref","first-page":"973","DOI":"10.21437\/Eurospeech.1993-229","volume-title":"Proceedings of Eurospeech","author":"Kneser","year":"1993"},{"key":"2026040313315344400_ref091","volume-title":"Proceed- ings of ICSLP","author":"Kuhn","year":"1998"},{"key":"2026040313315344400_ref092","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0167-6393(98)00061-2","article-title":"Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition,","volume":"26","author":"Kumar","year":"1998","journal-title":"Speech Communica- tion"},{"issue":"3","key":"2026040313315344400_ref093","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1109\/TSA.2005.858064","article-title":"Maximum entropy direct models for speech recognition,","volume":"14","author":"Kuo","year":"2006","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"2026040313315344400_ref094","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1006\/csla.2001.0186","article-title":"Lightly supervised and unsupervised acoustic model training","volume":"16","author":"Lamel","year":"2002","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref095","volume-title":"Proceedings of ICASSP","author":"Layton","year":"2006"},{"key":"2026040313315344400_ref096","volume-title":"Proceedings of ICASSP","author":"Lee","year":"1996"},{"issue":"2","key":"2026040313315344400_ref097","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","article-title":"Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models","volume":"9","author":"Leggetter","year":"1995","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref098","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/S0885-2308(86)80009-2","article-title":"Continuously variable duration hidden Markov models for automatic speech recognition","volume":"1","author":"Levinson","year":"1986","journal-title":"Computer Speech and Language"},{"issue":"4","key":"2026040313315344400_ref099","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1002\/j.1538-7305.1983.tb03114.x","article-title":"An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition","volume":"62","author":"Levinson","year":"1983","journal-title":"Bell Systems Technical Journal"},{"key":"2026040313315344400_ref100","volume-title":"Proceedings of ICASSP","author":"Li","year":"2007"},{"key":"2026040313315344400_ref101","volume-title":"Uncertainty Decoding For Noise Robust Speech Recognition","author":"Liao","year":"2007"},{"key":"2026040313315344400_ref102","first-page":"3129","volume-title":"Proceedings of Interspeech","author":"Liao","year":"2005"},{"key":"2026040313315344400_ref103","volume-title":"Proceedings of ICSLP","author":"Liao","year":"2006"},{"key":"2026040313315344400_ref104","volume-title":"Proceedings of ICASSP","author":"Liao","year":"2007"},{"key":"2026040313315344400_ref105","volume-title":"Proceedings of Eurospeech","author":"Lippmann","year":"1997"},{"issue":"4","key":"2026040313315344400_ref106","doi-asserted-by":"crossref","first-page":"1414","DOI":"10.1109\/TASL.2006.889804","article-title":"Automatic model complexity control using marginalized discriminative growth functions","volume":"15","author":"Liu","year":"2007","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"2","key":"2026040313315344400_ref107","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/0167-6393(92)90016-Z","article-title":"Experiments with a nonlinear spectral subtractor (NSS), hidden Markov models and the projection, for robust speech recogni- tion in cars","volume":"11","author":"Lockwood","year":"1992","journal-title":"Speech Communication"},{"key":"2026040313315344400_ref108","volume-title":"The Harpy Speech Recognition System","author":"Lowerre","year":"1976"},{"key":"2026040313315344400_ref109","first-page":"2044","volume-title":"Proceedings of ICASSP","author":"Luo","year":"1999"},{"key":"2026040313315344400_ref110","volume-title":"Proceedings of ICASSP","author":"Ma","year":"1059"},{"key":"2026040313315344400_ref111","volume-title":"Proceedings of Interspeech","author":"Macherey","year":"2005"},{"key":"2026040313315344400_ref112","doi-asserted-by":"crossref","DOI":"10.1109\/TASL.2006.885941","article-title":"Kernel eigenspace-based MLLR adaptation","author":"Mak","year":"2007","journal-title":"IEEE Transactions Speech and Audio Processing"},{"key":"2026040313315344400_ref113","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TSA.2005.851971","article-title":"Kernel eigenvoices speaker adaptation","volume":"13","author":"Mak","year":"2005","journal-title":"IEEE Transactions Speech and Audio Processing"},{"issue":"4","key":"2026040313315344400_ref114","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1006\/csla.2000.0152","article-title":"Finding consensus among words: Lattice- based word error minimisation","volume":"14","author":"Mangu","year":"2000","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref115","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.21437\/Eurospeech.1995-312","volume-title":"Proceedings of Eurospeech","author":"Martin","year":"1995"},{"key":"2026040313315344400_ref116","article-title":"The BBN 2001 English conversational speech system,","author":"Matsoukas","year":"2001","journal-title":"Presentation at 2001 NIST Large Vocabulary Conversational Speech Workshop"},{"issue":"5","key":"2026040313315344400_ref117","doi-asserted-by":"crossref","first-page":"1541","DOI":"10.1109\/TASL.2006.878257","article-title":"Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN\/LIMSI sys- tem,","volume":"14","author":"Matsoukas","year":"2006","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"2026040313315344400_ref118","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1006\/csla.1997.0036","article-title":"-best unsupervised speaker adaptation for speech recognition,","volume":"12","author":"Matsui","year":"1998","journal-title":"Computer Speech and Language"},{"issue":"1","key":"2026040313315344400_ref119","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1109\/TASL.2006.876778","article-title":"Discriminative training for large-vocabulary speech recognition using mini- mum classification error","volume":"15","author":"McDermott","year":"2007","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"2026040313315344400_ref120","volume-title":"Proceedings of ICSLP","author":"McDonough","year":"1998"},{"key":"2026040313315344400_ref121","volume-title":"Proceed- ings of ICASSP","author":"Meyer","year":"2002"},{"issue":"1","key":"2026040313315344400_ref122","doi-asserted-by":"crossref","DOI":"10.1006\/csla.2001.0184","article-title":"Weighted finite state transducers in speech recognition","volume":"16","author":"Mohri","year":"2002","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref123","volume-title":"Speech recognition in noisy environments","author":"Moreno","year":"1996"},{"key":"2026040313315344400_ref124","first-page":"733","volume-title":"Proceedings of ICASSP","author":"Moreno","year":"1996"},{"issue":"4","key":"2026040313315344400_ref125","doi-asserted-by":"crossref","first-page":"814","DOI":"10.1109\/TASSP.1983.1164173","article-title":"A decision theoretic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood","volume":"31","author":"Nadas","year":"1983","journal-title":"IEEE Transactions on Acoustics Speech and Signal Pro- cessing"},{"key":"2026040313315344400_ref126","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.21437\/Eurospeech.1995-282","volume-title":"Proceedings of Eurospeech","author":"Neumeyer","year":"1995"},{"issue":"1","key":"2026040313315344400_ref127","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1006\/csla.1994.1001","article-title":"On structuring probabilistic dependences in stochastic language modelling","volume":"8","author":"Ney","year":"1994","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref128","volume-title":"Proceedings of ICASSP","author":"Nguyen","year":"2004"},{"key":"2026040313315344400_ref129","volume-title":"Proceedings of ICASSP","author":"Normandin","year":"1991"},{"key":"2026040313315344400_ref130","doi-asserted-by":"crossref","first-page":"405","DOI":"10.3115\/1075812.1075905","volume-title":"Proceedings of Human Language Technology Workshop","author":"Odell","year":"1994"},{"key":"2026040313315344400_ref131","volume-title":"Proceedings of ICSLP","author":"Olsen","year":"2002"},{"issue":"1","key":"2026040313315344400_ref132","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1006\/csla.1996.0022","article-title":"A word graph algorithm for large vocabulary continuous speech recognition","volume":"11","author":"Ortmanns","year":"1997","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref133","first-page":"128","author":"Padmanabhan","year":"2000","journal-title":"Proceedings of ITRW ASR2000: ASR Challenges for the New Millenium"},{"key":"2026040313315344400_ref134","author":"Pallet","year":"1998"},{"key":"2026040313315344400_ref135","first-page":"693","volume-title":"Proceedings of ICASSP","author":"Paul","year":"1991"},{"key":"2026040313315344400_ref136","volume-title":"Discriminative Training for Large Vocabulary Speech Recognition","author":"Povey","year":"2004"},{"key":"2026040313315344400_ref137","volume-title":"Proceedings of EuroSpeech","author":"Povey","year":"2003"},{"key":"2026040313315344400_ref138","volume-title":"Proceedings of ICASSP","author":"Povey","year":"2005"},{"key":"2026040313315344400_ref139","volume-title":"Proceedings of ICASSP","author":"Povey","year":"2002"},{"key":"2026040313315344400_ref140","first-page":"651","article-title":"The DARPA 1000-word Resource Management database for continuous speech recognition","volume":"1","author":"Price","year":"1988","journal-title":"Proceed- ings of ICASSP"},{"issue":"2","key":"2026040313315344400_ref141","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proceedings of IEEE"},{"issue":"6","key":"2026040313315344400_ref142","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1002\/j.1538-7305.1985.tb00272.x","article-title":"Recognition of isolated digits using HMMs with continuous mixture densities","volume":"64","author":"Rabiner","year":"1985","journal-title":"AT and T Technical Journal"},{"issue":"5","key":"2026040313315344400_ref143","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1109\/MSP.2005.1511828","article-title":"Missing feature approaches in speech recognition","volume":"22","author":"Raj","year":"2005","journal-title":"IEEE Signal Processing Magazine"},{"key":"2026040313315344400_ref144","first-page":"576","volume-title":"Proceedings of ICASSP","author":"Richardson","year":"1995"},{"issue":"2","key":"2026040313315344400_ref145","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2006.06.006","article-title":"Discriminative \ud835\udc41 -gram language mod- elling","volume":"21","author":"Roark","year":"2007","journal-title":"Computer Speech and Language"},{"issue":"2","key":"2026040313315344400_ref146","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.csl.2003.09.004","article-title":"Factor analysed hidden Markov models for speech recognition","volume":"18","author":"Rosti","year":"2004","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref147","first-page":"5","volume-title":"Proceedings of ICASSP","author":"Russell","year":"1985"},{"key":"2026040313315344400_ref148","volume-title":"Proceedings of ICASSP","author":"Saon","year":"2004"},{"key":"2026040313315344400_ref149","volume-title":"Proceedings of ICASSP","author":"Saon","year":"2000"},{"key":"2026040313315344400_ref150","volume-title":"EARS STT workshop","author":"Saon","year":"2003"},{"key":"2026040313315344400_ref151","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1109\/89.824696","article-title":"Maximum likelihood and minimum classifica- tion error factor analysis for automatic speech recognition","volume":"8","author":"Saul","year":"2000","journal-title":"IEEE Transac- tions on Speech and Audio Processing"},{"key":"2026040313315344400_ref152","first-page":"119","volume-title":"Proceedings of IEEE ASRU Workshop","author":"Schluter","year":"1999"},{"key":"2026040313315344400_ref153","first-page":"701","volume-title":"Proceedings of ICASSP","author":"Schwartz","year":"1991"},{"key":"2026040313315344400_ref154","volume-title":"Proceedings of ICASSP","author":"Schwenk","year":"1999"},{"issue":"4","key":"2026040313315344400_ref155","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1016\/j.specom.2004.03.006","article-title":"A Bayesian framework for spectrographic mask estimation for missing feature speech recognition","volume":"43","author":"Seltzer","year":"2004","journal-title":"Speech Communication"},{"key":"2026040313315344400_ref156","first-page":"1249","article-title":"Large margin Gaussian mixture modelling for auto- matic speech recognition,","author":"Sha","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026040313315344400_ref157","volume-title":"Proceedings of ASRU\u201997","author":"Shinoda","year":"1997"},{"key":"2026040313315344400_ref158","volume-title":"Proceedings of ICASSP","author":"Sim","year":"2004"},{"key":"2026040313315344400_ref159","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1016\/j.csl.2007.03.004","article-title":"Discriminative semi-parametric trajectory models for speech recognition","volume":"21","author":"Sim","year":"2007","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref160","article-title":"The CU-HTK Mandarin broadcast news transcription system,","author":"Sinha","year":"2006","journal-title":"Proceed- ings of ICASSP"},{"key":"2026040313315344400_ref161","volume-title":"Proceedings of InterSpeech","author":"Sinha"},{"key":"2026040313315344400_ref162","volume-title":"Proceedings of ICASSP","author":"Siohan","year":"2005"},{"key":"2026040313315344400_ref163","volume-title":"Proceed- ings of ICASSP","author":"Soltau","year":"2005"},{"issue":"7","key":"2026040313315344400_ref164","doi-asserted-by":"crossref","first-page":"2130","DOI":"10.1109\/TASL.2007.901836","article-title":"Transforming binary uncertainties for robust speech recognition","volume":"15","author":"Srinivasan","year":"2007","journal-title":"IEEE Transactions of Audio, Speech and Language Pro- cessing"},{"key":"2026040313315344400_ref165","volume-title":"Proceedings of EuroSpeech","author":"Stolcke","year":"1997"},{"key":"2026040313315344400_ref166","volume-title":"Learning Structured Prediction Models: A Large Margin Approach","author":"Tasker","year":"2004"},{"issue":"3","key":"2026040313315344400_ref167","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/0885-2308(90)90008-T","article-title":"Best-first enumeration of paths through a lattice \u2014 An active chart parsing solution","volume":"4","author":"Thompson","year":"1990","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref168","volume-title":"Text to speech synthesis: New paradigms and advances","author":"Tokuda","year":"2004"},{"key":"2026040313315344400_ref169","volume-title":"Proceedings Beyond HMM Workshop","author":"Tokuda","year":"2004"},{"issue":"5","key":"2026040313315344400_ref170","article-title":"An overview of automatic speaker diarisa- tion systems","volume":"14","author":"Tranter","year":"2006","journal-title":"IEEE Transactions Speech and Audio Processing"},{"issue":"3","key":"2026040313315344400_ref171","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1109\/TSA.2005.845806","article-title":"Discriminative linear trans- forms for feature normalisation and speaker adaptation in HMM estimation","volume":"13","author":"Tsakalidis","year":"2005","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"2026040313315344400_ref172","first-page":"49","volume-title":"Proceedings of ICASSP","author":"Uebel","year":"2001"},{"key":"2026040313315344400_ref173","volume-title":"Proceedings of ICSLP","author":"Valtchev","year":"1994"},{"key":"2026040313315344400_ref174","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1016\/S0167-6393(97)00029-0","article-title":"MMIE train- ing of large vocabulary recognition systems","volume":"22","author":"Valtchev","year":"1997","journal-title":"Speech Communication"},{"key":"2026040313315344400_ref175","volume-title":"Proceedings of ICASSP","author":"Vanhoucke","year":"2003"},{"key":"2026040313315344400_ref176","first-page":"845","author":"Varga","year":"1990","journal-title":"Proceedings of ICASSP"},{"key":"2026040313315344400_ref177","first-page":"260","volume-title":"IEEE Transactions on Information Theory","author":"Viterbi","year":"1982"},{"key":"2026040313315344400_ref178","first-page":"1835","volume-title":"Proceedings of ICASSP","author":"Wallhof","year":"2000"},{"key":"2026040313315344400_ref179","volume-title":"Proceedings of ICASSP","author":"Wang","year":"2007"},{"key":"2026040313315344400_ref180","volume-title":"Proceedings of ASRU","author":"Wang","year":"2003"},{"key":"2026040313315344400_ref181","first-page":"384","volume-title":"Proceedings of ICASSP","author":"Wellekens","year":"1987"},{"key":"2026040313315344400_ref182","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1006\/csla.2001.0182","article-title":"Large scale discriminative training of hidden Markov models for speech recognition","volume":"16","author":"Woodland","year":"2002","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref183","first-page":"1133","volume-title":"Proceedings of ICSLP\u201996","author":"Woodland","year":"1996"},{"key":"2026040313315344400_ref184","volume-title":"Proceedings of ICASSP","author":"Woodland","year":"1992"},{"key":"2026040313315344400_ref185","article-title":"The development of the 1996 HTK broadcast news transcription system,","author":"Woodland","year":"1997","journal-title":"Proceedings of Human Language Technology Workshop"},{"key":"2026040313315344400_ref186","volume-title":"Proceedings of ICASSP","author":"Wu","year":"2006"},{"key":"2026040313315344400_ref187","first-page":"351","article-title":"Generating multiple solutions from connected word DP recogni- tion algorithms,","volume":"6","author":"Young","year":"1984","journal-title":"Proceedings of IOA Autumn Conference"},{"key":"2026040313315344400_ref188","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1006\/csla.1998.0101","article-title":"Speech recognition evaluation: A review of the US CSR and LVCSR programmes","volume":"12","author":"Young","year":"1998","journal-title":"Computer Speech and Language"},{"key":"2026040313315344400_ref189","author":"Young","year":"2006","journal-title":"The HTK Book (for HTK Version 3.4)"},{"key":"2026040313315344400_ref190","doi-asserted-by":"crossref","first-page":"307","DOI":"10.3115\/1075812.1075885","volume-title":"Proceedings of Human Language Tech- nology Workshop","author":"Young","year":"1994"},{"key":"2026040313315344400_ref191","author":"Young","year":"1989"},{"issue":"1","key":"2026040313315344400_ref192","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0885-2308(91)90018-L","article-title":"The use of syntax and multiple alternatives in the VODIS voice operated database inquiry system","volume":"5","author":"Young","year":"1991","journal-title":"Computer Speech and Language"},{"issue":"5","key":"2026040313315344400_ref193","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1109\/TSA.2005.858555","article-title":"Discriminative cluster adaptive training","volume":"14","author":"Yu","year":"2006","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"6","key":"2026040313315344400_ref194","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1109\/TASL.2007.901300","article-title":"Bayesian adaptive inference and adaptive training","volume":"15","author":"Yu","year":"2007","journal-title":"IEEE Transactions Speech and Audio Processing"},{"key":"2026040313315344400_ref195","volume-title":"Proceedings of InterSpeech","author":"Yu","year":"2007"},{"key":"2026040313315344400_ref196","volume-title":"Proceedings of ICASSP","author":"Zen","year":"2004"},{"key":"2026040313315344400_ref197","volume-title":"Proceedings of ICASSP","author":"Zhang","year":"2006"},{"key":"2026040313315344400_ref198","author":"Zheng","year":"2005","journal-title":"Proceedings of InterSpeech"},{"key":"2026040313315344400_ref199","volume-title":"Proceedings of ICSLP","author":"Zhu","year":"2004"},{"key":"2026040313315344400_ref200","volume-title":"Speech Recognition with Dynamic Bayesian Networks","author":"Zweig","year":"1998"},{"key":"2026040313315344400_ref201","volume-title":"Proceedings of ICASSP","author":"Zweig","year":"2000"}],"container-title":["Foundations and Trends\u00ae in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftsig\/article-pdf\/1\/3\/195\/11052538\/2000000004en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftsig\/article-pdf\/1\/3\/195\/11052538\/2000000004en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:55:23Z","timestamp":1777488923000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftsig\/article\/1\/3\/195\/1328584\/The-Application-of-Hidden-Markov-Models-in-Speech"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,2,21]]},"references-count":201,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2008,2,21]]}},"URL":"https:\/\/doi.org\/10.1561\/2000000004","relation":{},"ISSN":["1932-8346","1932-8354"],"issn-type":[{"value":"1932-8346","type":"print"},{"value":"1932-8354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,2,21]]}}}