{"id":"https://openalex.org/W2099379741","doi":"https://doi.org/10.21437/eurospeech.2003-191","title":"Speech recognition with a generative factor analyzed hidden Markov model","display_name":"Speech recognition with a generative factor analyzed hidden Markov model","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2099379741","doi":"https://doi.org/10.21437/eurospeech.2003-191","mag":"2099379741"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5103119755","display_name":"Kaisheng Yao","orcid":"https://orcid.org/0000-0002-8949-9367"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaisheng Yao","raw_affiliation_strings":["University of California,  San Diego"],"affiliations":[{"raw_affiliation_string":"University of California,  San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046089538","display_name":"Kuldip K. Paliwal","orcid":"https://orcid.org/0000-0002-3553-3662"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kuldip K. Paliwal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5022408850","display_name":"Te-Won Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Te-Won Lee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103119755"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.468,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75004746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"849","last_page":"852"},"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":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.9628187417984009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6298092603683472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5978844165802002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5912854075431824},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.5487889647483826},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.53753262758255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5020730495452881},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4659845232963562},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4603898227214813},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.39035215973854065},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3645837903022766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30465590953826904},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.291462779045105},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.2751516103744507},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.241539865732193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23181778192520142},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16170135140419006}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9628187417984009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6298092603683472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5978844165802002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5912854075431824},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.5487889647483826},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.53753262758255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020730495452881},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4659845232963562},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4603898227214813},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.39035215973854065},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3645837903022766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30465590953826904},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.291462779045105},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.2751516103744507},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.241539865732193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23181778192520142},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16170135140419006},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/1787","is_oa":false,"landing_page_url":"http://hdl.handle.net/10072/1787","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"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 output"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2137944862","https://openalex.org/W2137969290"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2379938888","https://openalex.org/W4246505579","https://openalex.org/W2134386692","https://openalex.org/W2116722627","https://openalex.org/W2799426416","https://openalex.org/W2537260108","https://openalex.org/W1977445474","https://openalex.org/W2566202039","https://openalex.org/W2792905593"],"abstract_inverted_index":{"We":[0,102],"present":[1],"a":[2,15,39,62,87],"generative":[3],"factor":[4],"analyzed":[5],"hidden":[6,33],"Markov":[7],"model":[8,130],"(GFA-HMM)":[9],"for":[10,75],"automatic":[11],"speech":[12],"recognition.":[13],"In":[14],"traditional":[16,100,116],"HMM,":[17],"the":[18,58,81,93,109,119],"observation":[19,46,97],"vectors":[20,50,60,98],"are":[21,29,54,65],"represented":[22],"by":[23],"mixture":[24],"of":[25,41,45,80,92,96,122,129],"Gaussians":[26],"(MoG)":[27],"that":[28,108],"dependent":[30,56],"on":[31],"discrete-valued":[32],"state":[34],"sequence.":[35],"The":[36,83],"GFA-HMM":[37,84,110],"introduces":[38],"hierarchy":[40],"continuous-valued":[42],"latent":[43,49,59],"representation":[44,91],"vectors,":[47],"where":[48],"in":[51,61],"one":[52],"level":[53,64],"acoustic-unit":[55,66],"and":[57],"higher":[63],"independent.":[67],"An":[68],"expectation":[69],"maximization":[70],"(EM)":[71],"algorithm":[72],"is":[73],"derived":[74],"maximum":[76],"likelihood":[77],"parameter":[78],"estimation":[79],"model.":[82],"can":[85,111],"achieve":[86,112],"much":[88,126],"more":[89],"compact":[90],"intra-frame":[94],"statistics":[95],"than":[99],"HMM.":[101],"conducted":[103],"an":[104],"experiment":[105],"to":[106],"show":[107],"better":[113],"performances":[114],"over":[115],"HMM":[117],"with":[118],"same":[120],"amount":[121],"training":[123],"data":[124],"but":[125],"smaller":[127],"number":[128],"parameters.":[131]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}