{"id":"https://openalex.org/W49713143","doi":"https://doi.org/10.21437/eurospeech.2001-193","title":"Maximum-likelihood training of a bipartite acoustic model for speech recognition","display_name":"Maximum-likelihood training of a bipartite acoustic model for speech recognition","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W49713143","doi":"https://doi.org/10.21437/eurospeech.2001-193","mag":"49713143"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5059987704","display_name":"Florent Perronnin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Florent Perronnin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103230324","display_name":"Roland K\u00fchn","orcid":"https://orcid.org/0000-0002-1485-140X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roland Kuhn","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111420783","display_name":"Jean-Claude Junqua","orcid":null},"institutions":[{"id":"https://openalex.org/I1283155146","display_name":"Panasonic (Japan)","ror":"https://ror.org/011tm7n37","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283155146"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jean-Claude Junqua","raw_affiliation_strings":["PANASONIC"],"affiliations":[{"raw_affiliation_string":"PANASONIC","institution_ids":["https://openalex.org/I1283155146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059987704"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00625332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"683","last_page":"686"},"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":0.9968000054359436,"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":0.9955999851226807,"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/timit","display_name":"TIMIT","score":0.885216236114502},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6891417503356934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6746760010719299},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6147568225860596},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6134570837020874},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.5450322031974792},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4852161705493927},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4682741165161133},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4340862035751343},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42439544200897217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3943578898906708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37430500984191895},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2532641291618347},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.0994739830493927}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.885216236114502},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6891417503356934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6746760010719299},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6147568225860596},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6134570837020874},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.5450322031974792},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4852161705493927},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4682741165161133},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4340862035751343},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42439544200897217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3943578898906708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37430500984191895},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2532641291618347},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0994739830493927},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2001-193","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W118865840","https://openalex.org/W137536304","https://openalex.org/W1526415695","https://openalex.org/W1602232401","https://openalex.org/W2099111195","https://openalex.org/W2126160986","https://openalex.org/W2158069733","https://openalex.org/W2165108269"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2121652828","https://openalex.org/W4288040805","https://openalex.org/W2962874523"],"abstract_inverted_index":{"In":[0],"a":[1,6,13,40,55,147],"recent":[2],"paper,":[3],"we":[4,68],"described":[5],"compact,":[7],"context-dependent":[8,51],"acoustic":[9,171],"model":[10,31],"incorporating":[11],"strong":[12],"priori":[14],"knowledge":[15],"and":[16,94,132,159,166,181],"designed":[17],"to":[18,79],"support":[19],"extremely":[20],"rapid":[21],"speaker":[22],"adaptation":[23,93,111,131,136],"[9].":[24],"The":[25],"two":[26],"parts":[27,82],"of":[28,43,58,83,110,117,163,170],"this":[29],"\u201cbipartite\u201d":[30],"are:":[32],"1.":[33],"A":[34,49],"speakerdependent,":[35],"context-independent":[36],"(SDCI)":[37],"part":[38,53,162],"with":[39,54],"small":[41,108],"number":[42,57],"parameters":[44,59],"called":[45,60],"the":[46,61,65,71,74,84,90,98,152,155,160,164,176],"\u201ceigencentroid\u201d.":[47],"2.":[48],"speaker-independent,":[50],"(SICD)":[52],"large":[56],"\u201cdelta":[62],"trees\u201d.":[63],"For":[64],"first":[66,91],"time,":[67],"describe":[69],"in":[70],"current":[72],"paper":[73,87,153],"iterative":[75],"maximum-likelihood":[76],"procedure":[77],"employed":[78],"train":[80],"both":[81],"model.":[85],"This":[86],"also":[88],"gives":[89],"unsupervised":[92,135],"self-adaptation":[95,145],"results":[96],"for":[97,129,134,144],"new":[99],"model,":[100,165],"showing":[101],"that":[102],"it":[103,141],"outperforms":[104],"standard":[105],"techniques":[106],"when":[107],"amounts":[109],"data":[112],"(10":[113],"sec.":[114],"or":[115],"less":[116],"sp":[118],"eech)":[119],"are":[120],"available.":[121],"Relative":[122],"error":[123],"rate":[124],"reduction":[125],"(ERR)":[126],"is":[127,142,173],"12.1%":[128],"supervised":[130],"11.2%":[133],"on":[137,146],"three":[138],"TIMIT":[139,149],"sentences;":[140],"10.4%":[143],"single":[148],"sentence.":[150],"Finally,":[151],"analyzes":[154],"correlation":[156],"between":[157],"sex":[158],"SDCI":[161],"shows":[167],"how":[168],"modeling":[169],"variability":[172],"affected":[174],"by":[175],"explicit":[177],"separation":[178],"into":[179],"SD":[180],"CD":[182],"components.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}