{"id":"https://openalex.org/W58778773","doi":"https://doi.org/10.21437/eurospeech.1997-546","title":"Adaptation of hidden Markov models using multiple stochastic transformations","display_name":"Adaptation of hidden Markov models using multiple stochastic transformations","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W58778773","doi":"https://doi.org/10.21437/eurospeech.1997-546","mag":"58778773"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5031538820","display_name":"Vassilios Diakoloukas","orcid":"https://orcid.org/0000-0002-1030-2892"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Vassilios Diakoloukas","raw_affiliation_strings":["Technical University of Crete"],"affiliations":[{"raw_affiliation_string":"Technical University of Crete","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030929323","display_name":"Vassilios Digalakis","orcid":"https://orcid.org/0000-0002-1255-8939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vassilios Digalakis","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031538820"],"corresponding_institution_ids":["https://openalex.org/I55741626"],"apc_list":null,"apc_paid":null,"fwci":0.585,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71883619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2063","last_page":"2066"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9983000159263611,"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":0.8082376718521118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7874243259429932},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7390265464782715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7386114597320557},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6697028279304504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5588551163673401},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345218777656555},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5031992793083191},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4934731721878052},{"id":"https://openalex.org/keywords/decipher","display_name":"DECIPHER","score":0.48393040895462036},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42611774802207947}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8082376718521118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874243259429932},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7390265464782715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7386114597320557},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6697028279304504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5588551163673401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345218777656555},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5031992793083191},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4934731721878052},{"id":"https://openalex.org/C164614171","wikidata":"https://www.wikidata.org/wiki/Q5204775","display_name":"DECIPHER","level":2,"score":0.48393040895462036},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42611774802207947},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1997-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W125108960","https://openalex.org/W1967487032","https://openalex.org/W2082474452","https://openalex.org/W2146871184"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366"],"abstract_inverted_index":{"The":[0,133],"recognition":[1,43,51,125,142],"accuracy":[2,126],"in":[3,42],"recent":[4],"large":[5],"vocabulary":[6],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"systems":[11],"is":[12],"highly":[13],"related":[14],"to":[15,37,69],"the":[16,20,31,50,71,75,78,92,96,99,124,128],"existing":[17],"mismatch":[18],"between":[19],"training":[21,32],"and":[22,33,73,111,115,127],"test":[23],"sets.":[24],"For":[25],"example,":[26],"dialect":[27,112],"di":[28],"erences":[29],"across":[30],"testing":[34],"speakers":[35],"result":[36],"a":[38,86],"signi":[39,121],"cant":[40],"degradation":[41],"performance.":[44],"Some":[45],"popular":[46],"adaptation":[47,88,113],"approaches":[48],"improve":[49],"performance":[52],"of":[53,77,98,130],"speech":[54,141],"recognizers":[55],"based":[56],"on":[57],"hidden":[58],"Markov":[59],"models":[60],"with":[61,138],"continuous":[62],"mixture":[63,79,100],"densities":[64],"by":[65,102],"using":[66,103],"linear":[67],"transforms":[68],"adapt":[70],"means,":[72],"possibly":[74],"covariances":[76,97],"Gaussians.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,116],"propose":[85],"novel":[87],"technique":[89],"that":[90,118],"adapts":[91],"means":[93],"and,":[94],"optionally,":[95],"Gaussians":[101],"multiple":[104],"stochastic":[105],"transformations.":[106],"We":[107],"perform":[108],"both":[109],"speaker":[110],"experiments,":[114],"show":[117],"our":[119,131],"method":[120],"cantly":[122],"improves":[123],"robustness":[129],"system.":[132,143],"experiments":[134],"are":[135],"carried":[136],"out":[137],"SRI's":[139],"DECIPHER":[140]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}