{"id":"https://openalex.org/W2587275078","doi":"https://doi.org/10.1109/slt.2016.7846323","title":"High quality agreement-based semi-supervised training data for acoustic modeling","display_name":"High quality agreement-based semi-supervised training data for acoustic modeling","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2587275078","doi":"https://doi.org/10.1109/slt.2016.7846323","mag":"2587275078"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","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/A5026916144","display_name":"F\u00e9lix de Chaumont Quitry","orcid":"https://orcid.org/0000-0003-4959-0016"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix de Chaumont Quitry","raw_affiliation_strings":["Google Inc., Mountain View, CA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, CA, US","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047650531","display_name":"Asa Oines","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asa Oines","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Weinstein","raw_affiliation_strings":["Google Inc., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"592","last_page":"596"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8611167669296265},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.666262686252594},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6639519929885864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6634098291397095},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6335645914077759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5587140321731567},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5255985260009766},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4928576946258545},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48533573746681213},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4693912863731384},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43964633345603943},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07407185435295105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8611167669296265},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.666262686252594},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6639519929885864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6634098291397095},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6335645914077759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5587140321731567},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5255985260009766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4928576946258545},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48533573746681213},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4693912863731384},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43964633345603943},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07407185435295105},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/slt.2016.7846323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W81442308","https://openalex.org/W82886505","https://openalex.org/W1600744878","https://openalex.org/W1993952617","https://openalex.org/W2085598899","https://openalex.org/W2127141656","https://openalex.org/W2139453310","https://openalex.org/W2189391786","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2294962864","https://openalex.org/W6648736669","https://openalex.org/W6696934422","https://openalex.org/W6696982659"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"This":[0,100],"paper":[1],"describes":[2],"a":[3],"new":[4,135],"technique":[5],"to":[6,31,71,103,116],"automatically":[7,105],"obtain":[8],"large":[9],"high-quality":[10],"training":[11],"speech":[12,77,107],"corpora":[13,108],"for":[14],"acoustic":[15,136],"modeling.":[16],"Traditional":[17],"approaches":[18],"select":[19],"utterances":[20],"based":[21],"on":[22,47,57,143],"confidence":[23],"thresholds":[24],"and":[25,43,66],"other":[26],"heuristics.":[27],"We":[28],"propose":[29],"instead":[30],"use":[32,54],"an":[33,91],"ensemble":[34],"approach:":[35],"we":[36,53,82,123,132],"transcribe":[37],"each":[38],"utterance":[39],"using":[40,126],"several":[41],"recognizers,":[42],"only":[44],"keep":[45],"those":[46,117,140],"which":[48,138],"they":[49,87],"agree.":[50],"The":[51],"recognizers":[52],"are":[55,110],"trained":[56,141],"data":[58,130,146],"from":[59],"different":[60,73],"dialects":[61],"of":[62],"the":[63,96,127],"same":[64],"language,":[65],"this":[67,80,89],"diversity":[68],"leads":[69],"them":[70],"make":[72],"mistakes":[74],"in":[75,112],"transcribing":[76],"utterances.":[78],"In":[79],"work":[81],"show,":[83],"however,":[84],"that":[85,95,109,125],"when":[86],"agree,":[88],"is":[90,98],"extremely":[92],"strong":[93],"signal":[94],"transcript":[97,113],"correct.":[99],"allows":[101],"us":[102],"produce":[104],"transcribed":[106,119],"superior":[111],"correctness":[114],"even":[115],"manually":[118],"by":[120],"humans.":[121],"Furthermore,":[122],"show":[124],"produced":[128],"semi-supervised":[129],"sets,":[131],"can":[133],"train":[134],"models":[137],"outperform":[139],"solely":[142],"previously":[144],"available":[145],"sets.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}