{"id":"https://openalex.org/W99283740","doi":"https://doi.org/10.21437/interspeech.2010-23","title":"The use of sense in unsupervised training of acoustic models for ASR systems","display_name":"The use of sense in unsupervised training of acoustic models for ASR systems","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W99283740","doi":"https://doi.org/10.21437/interspeech.2010-23","mag":"99283740"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5102775511","display_name":"Rita Singh","orcid":"https://orcid.org/0000-0003-3743-0162"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rita Singh","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012372882","display_name":"Benjamin Lambert","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Lambert","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102775511"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.451,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69688511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2938","last_page":"2941"},"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":0.9993000030517578,"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"}},{"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":0.8048534393310547},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.638619601726532},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5901516675949097},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5652600526809692},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5598301291465759},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5407765507698059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5363345146179199},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49343958497047424},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4925742745399475},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4474030137062073},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.444683700799942},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44077250361442566},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.43131914734840393},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40634220838546753},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08372724056243896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8048534393310547},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.638619601726532},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5901516675949097},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5652600526809692},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5598301291465759},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5407765507698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5363345146179199},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49343958497047424},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4925742745399475},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4474030137062073},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.444683700799942},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44077250361442566},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.43131914734840393},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40634220838546753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08372724056243896},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"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:10.21437/interspeech.2010-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"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":7,"referenced_works":["https://openalex.org/W1590952807","https://openalex.org/W1989705153","https://openalex.org/W1998390196","https://openalex.org/W2138423722","https://openalex.org/W2150051359","https://openalex.org/W2157224593","https://openalex.org/W2171761326"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W1999699871","https://openalex.org/W2145230572","https://openalex.org/W4225124612","https://openalex.org/W3019226033"],"abstract_inverted_index":{"In":[0,71],"unsupervised":[1,102],"training":[2,16,103],"of":[3,30,46,61,83,89,104],"ASR":[4,23],"systems,":[5],"no":[6],"annotated":[7],"data":[8,31,119,146,154],"are":[9,18],"assumed":[10],"to":[11,41,91,152],"exist.":[12],"Word-level":[13],"annotations":[14],"for":[15,101],"audio":[17],"generated":[19],"iteratively":[20],"using":[21,120],"an":[22,76],"system.":[24],"At":[25],"each":[26],"iteration":[27],"a":[28,53,81,86,126,139],"subset":[29],"judged":[32],"as":[33],"having":[34],"the":[35,43,58,62,65,97,109,132],"most":[36],"reliable":[37],"transcriptions":[38],"is":[39,68,99,112],"selected":[40,140],"train":[42],"next":[44],"set":[45,143],"acoustic":[47,105],"models.":[48],"Data":[49],"selection":[50],"however":[51],"remains":[52],"difficult":[54],"problem,":[55],"particularly":[56,107],"when":[57,108],"error":[59],"rate":[60],"recognizer":[63],"providing":[64],"initial":[66,110,121],"annotation":[67,111],"very":[69],"high.":[70],"this":[72],"paper":[73],"we":[74],"propose":[75],"iterative":[77],"algorithm":[78,98],"that":[79,96,136],"uses":[80],"combination":[82],"likelihoods":[84],"and":[85,125,128],"simple":[87],"model":[88],"sense":[90],"select":[92],"data.":[93],"We":[94],"show":[95,135],"effective":[100],"models,":[106],"highly":[113],"erroneous.":[114],"Experiments":[115],"conducted":[116],"on":[117,138],"Fisher-1":[118],"models":[122],"from":[123,131,144],"Switchboard,":[124],"vocabulary":[127],"LM":[129],"derived":[130],"Google":[133],"N-grams,":[134],"performance":[137],"held-out":[141],"test":[142],"Fisher":[145],"improves":[147],"more":[148],"with":[149],"iterations":[150],"relative":[151],"likelihood-based":[153],"selection.":[155]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}