{"id":"https://openalex.org/W2136466519","doi":"https://doi.org/10.1109/icassp.2003.1198704","title":"Variable parameter Gaussian mixture hidden Markov modeling for speech recognition","display_name":"Variable parameter Gaussian mixture hidden Markov modeling for speech recognition","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2136466519","doi":"https://doi.org/10.1109/icassp.2003.1198704","mag":"2136466519"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198704","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I74760111","display_name":"Texas Instruments (United States)","ror":"https://ror.org/03vsmv677","country_code":"US","type":"company","lineage":["https://openalex.org/I74760111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Speech Technologies Laboratory, Texas Instruments, Inc., Dallas, TX, USA"],"affiliations":[{"raw_affiliation_string":"Speech Technologies Laboratory, Texas Instruments, Inc., Dallas, TX, USA","institution_ids":["https://openalex.org/I74760111"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":1.8685,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85818713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9976999759674072,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8027751445770264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6539351940155029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5897883176803589},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"Maximum-entropy Markov model","score":0.5245909094810486},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5068903565406799},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4813055098056793},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.47767242789268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47110894322395325},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44504523277282715},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.4397520422935486},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.4372292459011078},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.42669132351875305},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.36364006996154785},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3612041473388672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23656514286994934},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2066989541053772},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06926929950714111}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8027751445770264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539351940155029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5897883176803589},{"id":"https://openalex.org/C196956702","wikidata":"https://www.wikidata.org/wiki/Q6795829","display_name":"Maximum-entropy Markov model","level":5,"score":0.5245909094810486},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5068903565406799},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4813055098056793},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.47767242789268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47110894322395325},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44504523277282715},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.4397520422935486},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.4372292459011078},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.42669132351875305},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.36364006996154785},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3612041473388672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23656514286994934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2066989541053772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06926929950714111},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198704","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W6304026","https://openalex.org/W70797497","https://openalex.org/W1560013842","https://openalex.org/W2003146687","https://openalex.org/W2049633694","https://openalex.org/W2053742104","https://openalex.org/W2080921589","https://openalex.org/W2096708175","https://openalex.org/W2126109239","https://openalex.org/W2136439176","https://openalex.org/W2136466519","https://openalex.org/W2167342572","https://openalex.org/W2170429824","https://openalex.org/W3129711340","https://openalex.org/W6600255841","https://openalex.org/W6602929002","https://openalex.org/W6678544034","https://openalex.org/W6684863574"],"related_works":["https://openalex.org/W2382132287","https://openalex.org/W2161328464","https://openalex.org/W2379333870","https://openalex.org/W3113307220","https://openalex.org/W2118728396","https://openalex.org/W1542903750","https://openalex.org/W3164302780","https://openalex.org/W1510894296","https://openalex.org/W4250171007","https://openalex.org/W4385889111"],"abstract_inverted_index":{"To":[0],"improve":[1],"recognition,":[2],"speech":[3,15,23,34,45],"signals":[4],"corrupted":[5],"by":[6,37,60,127],"a":[7,78,102],"variety":[8],"of":[9,22,32,44,69,80,105,122],"noises":[10],"can":[11],"be":[12],"used":[13,91],"in":[14],"model":[16],"training.":[17,133],"Published":[18],"hidden":[19],"Markov":[20],"modeling":[21,43],"uses":[24],"multiple":[25],"Gaussian":[26],"distributions":[27],"to":[28,65,83,130],"cover":[29],"the":[30,33,38,42,52,75,84,86,106,119],"spread":[31],"distribution":[35],"caused":[36],"noises,":[39],"which":[40],"distracts":[41],"event":[46],"itself":[47],"and":[48,49,90],"possibly":[50],"sacrifices":[51],"performance":[53],"on":[54,114],"clean":[55],"speech.":[56],"We":[57],"extend":[58],"GMHMM":[59],"allowing":[61],"state":[62],"emission":[63],"parameters":[64,99],"change":[66],"as":[67,101],"function":[68,104],"an":[70],"environment-dependent":[71],"continuous":[72],"variable.":[73],"At":[74],"recognition":[76],"time,":[77],"set":[79],"HMMs":[81],"specific":[82],"given":[85],"environment":[87,107],"is":[88,109,116],"instantiated":[89],"for":[92],"recognition.":[93],"Variable":[94],"parameter":[95],"(VP)":[96],"HMM":[97],"with":[98],"modeled":[100],"polynomial":[103],"variable":[108],"developed.":[110],"Parameter":[111],"estimation":[112],"based":[113],"EM-algorithm":[115],"given.":[117],"With":[118],"same":[120],"number":[121],"mixtures,":[123],"VPHMM":[124],"reduces":[125],"WER":[126],"40%":[128],"compared":[129],"conventional":[131],"multi-condition":[132]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}