{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:23:11Z","timestamp":1780053791036,"version":"3.54.0"},"reference-count":118,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2012,11,1]],"date-time":"2012-11-01T00:00:00Z","timestamp":1351728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/msp.2012.2197156","type":"journal-article","created":{"date-parts":[[2012,10,19]],"date-time":"2012-10-19T20:36:29Z","timestamp":1350678989000},"page":"18-33","source":"Crossref","is-referenced-by-count":84,"title":["Large-Vocabulary Continuous Speech Recognition Systems: A Look at Some Recent Advances"],"prefix":"10.1109","volume":"29","author":[{"given":"George","family":"Saon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","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":"J R Stat Soc B"},{"key":"ref38","first-page":"2177","article-title":"Modeling with a subspace constraint on inverse covariance matrices","author":"axelrod","year":"0","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref33","first-page":"4057","article-title":"Boosted MMI for model and feature-space discriminative training","author":"povey","year":"0","journal-title":"Proc Int Conf Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415275"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163943"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325989"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947397"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/89.650310"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857792"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541101"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859163"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00061-2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/89.985541"},{"key":"ref24","first-page":"11","article-title":"Recent advances in robust speech recognition","author":"furui","year":"0","journal-title":"Proc ESCA Workshop on Robust Speech Recognition for Unknown Communication Channels"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref101","article-title":"The AT&T LVCSR 2000 system","author":"ljolje","year":"0","journal-title":"Proc NIST LVCSR Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.10.004"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref25","first-page":"806","article-title":"Large-vocabulary speech recognition under adverse acoustic environments","author":"deng","year":"0","journal-title":"Proc"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366912"},{"key":"ref51","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495640"},{"key":"ref58","first-page":"1145","article-title":"Feature and model space speaker adaptation with full covariance Gaussians","author":"povey","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref57","first-page":"128","article-title":"Lattice-based unsupervised MLLR for speaker adaptation","author":"padmanabhan","year":"0","journal-title":"Proc ITRI ASR2000 ASR Challenges for the New Millennium"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0010"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/MSP.2008.926652","article-title":"Discriminative learning in sequential pattern recognition—A unifying review for optimization-oriented speech recognition","volume":"25","author":"he","year":"2008","journal-title":"IEEE Signal Processing Mag"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960446"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879805"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.906178"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/89.568732"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879807"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878257"},{"key":"ref6","first-page":"2077","article-title":"Improved acoustic modeling for transcribing Arabic broadcast data","author":"lamel","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878264"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/1614108.1614141"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960443"},{"key":"ref7","first-page":"4309","article-title":"Improved morphological decomposition for Arabic broadcast news transcription","author":"ng","year":"0","journal-title":"Proc Int Conf Acoustic Speech and Signal Processing (ICASSP)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2022966"},{"key":"ref46","first-page":"2125","article-title":"Improved discriminative training using phone lattices","author":"zheng","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref45","first-page":"549","article-title":"Anatomy of an extremely fast LVCSR decoder","author":"saon","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref48","first-page":"920","article-title":"Penalty function maximization for large margin HMM training","author":"povey","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref44","first-page":"105","article-title":"Minimum phone error and I-smoothing for improved discriminative training","author":"povey","year":"0","journal-title":"Proc Int Conf Acoustic Speech and Signal Processing (ICASSP)"},{"key":"ref43","first-page":"537","article-title":"Discriminative training for continuous speech recognition","author":"reichl","year":"0","journal-title":"Proc European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref70","first-page":"437","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref76","first-page":"985","article-title":"A hierarchical Bayesian language model based on Pitman-Yor processes","author":"teh","year":"0","journal-title":"Proc Annu Meeting of the Association for Computational Linguistics"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040782"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref75","first-page":"181","article-title":"Improved backing-off for","author":"kneser","year":"0","journal-title":"Proc Int Conf Acoustic Speech and Signal Processing (ICASSP)"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/5.880084"},{"key":"ref79","first-page":"2167","article-title":"Topic-based language models using EM","author":"gildea","year":"0","journal-title":"Proc European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700829"},{"key":"ref62","first-page":"742","article-title":"Fast speaker adaptation using eigenspace-based maximum likelihood linear regression","author":"chen","year":"0","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860847"},{"key":"ref64","first-page":"1203","article-title":"Discriminative speaker adaptation with conditional maximum likelihood linear regression","author":"gunawardana","year":"0","journal-title":"Proc European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2007.09.001"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881692"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/89.536929"},{"key":"ref68","first-page":"869","article-title":"HMM adaptation using vector Taylor series for noisy speech recognition","author":"acero","year":"0","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325969"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947493"},{"key":"ref95","first-page":"1309","article-title":"A comparison of two LVR search optimization techniques","author":"kanthak","year":"0","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2155060"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.819943"},{"key":"ref93","first-page":"1977","article-title":"An architecture for rapid decoding of large vocabulary conversational speech","author":"saon","year":"0","journal-title":"Proc European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref106","first-page":"58","article-title":"Canonical state models for automatic speech recognition","author":"gales","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373470"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2010.06.003"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0147"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.011"},{"key":"ref90","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref103","first-page":"197","article-title":"Constructing ensembles of ASR systems using randomized decision trees","author":"siohan","year":"0","journal-title":"Proc Int Conf Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372916"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163907"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947558"},{"key":"ref110","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"tipping","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref99","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"0","journal-title":"Proc Speech Transcription Workshop"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372904"},{"key":"ref97","first-page":"1169","article-title":"Compiling large-context decision trees into finite-state transducers","author":"chen","year":"0","journal-title":"Proc European Conf Speech Communication and Technology (Eurospeech)"},{"key":"ref10","first-page":"1437","article-title":"Development of the SRI\/Nightingale Arabic ASR system","author":"vergyri","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495639"},{"key":"ref12","first-page":"2307","article-title":"Development of the GALE 2008 Mandarin LVCSR system","author":"plahl","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660211"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/79.536824"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0065-2458(03)60007-0"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.937999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932166"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050717"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1145\/1667053.1667056"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2009.932707"},{"key":"ref81","first-page":"5","article-title":"Dynamic language model adaptation using variational Bayes inference","author":"tam","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc (Interspeech)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1996.0011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"},{"key":"ref83","first-page":"467","article-title":"Class-based","volume":"18","author":"brown","year":"1992","journal-title":"Comput Linguist"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.828640"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2129911"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.845810"},{"key":"ref80","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960469"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.003"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858551"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.10.003"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620822"},{"key":"ref88","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/79\/6296521\/06296522.pdf?arnumber=6296522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T12:56:46Z","timestamp":1714481806000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6296522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":118,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/msp.2012.2197156","relation":{},"ISSN":["1053-5888"],"issn-type":[{"value":"1053-5888","type":"print"}],"subject":[],"published":{"date-parts":[[2012,11]]}}}