{"id":"https://openalex.org/W2019895003","doi":"https://doi.org/10.1109/asru.2009.5372953","title":"Acoustic modelling for speech recognition: Hidden Markov models and beyond?","display_name":"Acoustic modelling for speech recognition: Hidden Markov models and beyond?","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2019895003","doi":"https://doi.org/10.1109/asru.2009.5372953","mag":"2019895003"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5372953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"M.J.F. Gales","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050766679"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.08989608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8621129989624023},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8501806259155273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800468802452087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7453773617744446},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6703467965126038},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5180404186248779},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4695264399051666},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4670141339302063},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4603222906589508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4436173737049103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4332149028778076},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41253918409347534},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3964875340461731},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3321104943752289},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08609852194786072}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8621129989624023},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8501806259155273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800468802452087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7453773617744446},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6703467965126038},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5180404186248779},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4695264399051666},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4670141339302063},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4603222906589508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4436173737049103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4332149028778076},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41253918409347534},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3964875340461731},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3321104943752289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08609852194786072},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2009.5372953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5372953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:343978","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/343978/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6800000071525574,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W43454013","https://openalex.org/W162242150","https://openalex.org/W346349565","https://openalex.org/W1487784522","https://openalex.org/W1573570773","https://openalex.org/W1599512239","https://openalex.org/W1665196592","https://openalex.org/W1800365115","https://openalex.org/W1989093469","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2053567709","https://openalex.org/W2063541597","https://openalex.org/W2067117291","https://openalex.org/W2080921589","https://openalex.org/W2098601596","https://openalex.org/W2106404689","https://openalex.org/W2111421849","https://openalex.org/W2120025343","https://openalex.org/W2140409019","https://openalex.org/W2140595311","https://openalex.org/W2146871184","https://openalex.org/W2150907703","https://openalex.org/W2156615793","https://openalex.org/W2161513525","https://openalex.org/W3141839452"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W3148366653","https://openalex.org/W2121652828","https://openalex.org/W2004453227","https://openalex.org/W3033124456","https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W2122924390","https://openalex.org/W1955848339"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"models":[2,203],"(HMMs)":[3],"are":[4,48],"still":[5],"the":[6,21,23,28,39,64,73,125,141,167,171,188,194],"dominant":[7,142],"form":[8,143],"of":[9,27,63,84,109,111,166,170,187],"acoustic":[10],"model":[11],"used":[12,42],"in":[13,43],"automatic":[14],"speech":[15,45,112],"recognition":[16,46],"(ASR)":[17],"systems.":[18],"However":[19],"over":[20,72],"years":[22,56],"form,":[24],"and":[25,35,77,79,97,154,159,176,204],"training,":[26],"HMM":[29,196],"for":[30,144,178],"ASR":[31],"have":[32,69],"been":[33,70],"extended":[34],"modified,":[36],"so":[37],"that":[38,68],"current":[40,119,126,195],"forms":[41,91,169],"state-of-the-art":[44],"systems":[47,104],"very":[49],"different":[50],"to":[51,103,151],"those":[52],"originally":[53],"proposed":[54,71],"thirty":[55],"ago.":[57],"This":[58],"talk":[59,115,189],"will":[60,116,161,181,190,211],"review":[61],"two":[62],"more":[65],"important":[66],"extensions":[67,150],"years:":[74],"discriminative":[75,85,202],"training;":[76],"speaker":[78,138,145],"environment":[80],"adaptation.":[81,146],"The":[82,114,184],"use":[83],"training":[86,96,133,174,180],"is":[87,140],"now":[88],"common":[89],"with":[90],"based":[92,130,137,199],"on":[93,106,131,200],"minimum":[94,98],"Bayes'":[95],"classification":[99],"error":[100],"being":[101],"applied":[102],"trained":[105],"many":[107],"hundreds":[108],"hours":[110],"data.":[113],"describe":[117],"these":[118],"approaches,":[120,148],"as":[121,123,206,208],"well":[122,207],"discussing":[124],"trends":[127,160],"towards":[128],"schemes":[129],"large-margin":[132],"approaches.":[134],"Linear":[135],"transform":[136],"adaptation":[139],"Current":[147],"including":[149],"linear":[152],"transforms":[153],"model-based":[155],"noise":[156],"robustness":[157],"techniques,":[158],"also":[162],"be":[163,182,212],"described.":[164,213],"Details":[165],"various":[168],"adaptation/noise":[172],"transformation,":[173],"criterion":[175],"approaches":[177,210],"adaptive":[179],"given.":[183],"final":[185],"part":[186],"discuss":[191],"research":[192],"beyond":[193],"framework.":[197],"Schemes":[198],"both":[201],"functions,":[205],"non-parametric":[209]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}