{"id":"https://openalex.org/W2125107268","doi":"https://doi.org/10.1109/icassp.2011.5947393","title":"Lattice-based unsupervised acoustic model training","display_name":"Lattice-based unsupervised acoustic model training","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2125107268","doi":"https://doi.org/10.1109/icassp.2011.5947393","mag":"2125107268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5045988326","display_name":"Thiago Fraga-Silva","orcid":"https://orcid.org/0009-0001-7928-8929"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thiago Fraga-Silva","raw_affiliation_strings":["Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI, CNRS, Orsay, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]},{"raw_affiliation_string":"Spoken Language Processing Group, LIMSI - CNRS B.P. 133 91403 ORSAY CEDEX, FRANCE#TAB#","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1582,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.88771279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4656","last_page":"4659"},"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":0.9994999766349792,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7796077132225037},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6376649141311646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5470808148384094},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5444066524505615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.482229083776474},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.461347371339798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43714430928230286},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4346405863761902},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41384655237197876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2716911733150482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7796077132225037},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6376649141311646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5470808148384094},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5444066524505615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.482229083776474},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.461347371339798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43714430928230286},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4346405863761902},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41384655237197876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2716911733150482},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947393","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W23007503","https://openalex.org/W130324013","https://openalex.org/W1555037511","https://openalex.org/W1975113979","https://openalex.org/W2016243284","https://openalex.org/W2110073835","https://openalex.org/W2139698650","https://openalex.org/W2171761326","https://openalex.org/W2182251195","https://openalex.org/W6605298800","https://openalex.org/W6676769065","https://openalex.org/W6686130546"],"related_works":["https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W2037564206","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W1911859126"],"abstract_inverted_index":{"Unsupervised":[0],"acoustic":[1,42],"model":[2,43],"training":[3,91,98,107],"has":[4],"been":[5],"successfully":[6],"used":[7],"to":[8,40,53,58,82,84],"improve":[9],"the":[10,29,47,69,75,80,118],"performance":[11],"of":[12,22,79,103],"automatic":[13,38],"speech":[14],"recognition":[15,49],"systems":[16],"when":[17],"only":[18],"a":[19,85,100,109],"small":[20],"amount":[21],"manually":[23],"transcribed":[24],"data":[25],"is":[26,36,67,93],"available":[27],"for":[28],"target":[30],"domain.":[31],"The":[32,65,88],"most":[33],"common":[34],"approach":[35],"use":[37],"transcriptions":[39],"guide":[41],"estimation.":[44],"However,":[45],"since":[46],"best":[48],"hypotheses":[50,62,81],"are":[51],"known":[52],"contain":[54],"errors,":[55],"we":[56],"propose":[57],"consider":[59],"multiple":[60],"transcription":[61,112],"during":[63],"training.":[64,121],"idea":[66],"that":[68],"EM":[70],"process":[71],"can":[72],"benefit":[73],"from":[74],"estimated":[76],"posterior":[77],"probabilities":[78],"converge":[83],"better":[86],"solution.":[87],"proposed":[89],"unsupervised":[90],"method":[92],"based":[94],"on":[95,108],"lattices.":[96],"Lattice-based":[97],"gives":[99],"relative":[101],"improvement":[102],"2.2%":[104],"over":[105],"1-best":[106],"Broadcast":[110],"News":[111],"task":[113],"and":[114],"converges":[115],"faster":[116],"with":[117],"iterative":[119],"incremental":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}