{"id":"https://openalex.org/W2408234571","doi":"https://doi.org/10.1109/icassp.2016.7472804","title":"Data selection from multiple ASR systems' hypotheses for unsupervised acoustic model training","display_name":"Data selection from multiple ASR systems' hypotheses for unsupervised acoustic model training","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2408234571","doi":"https://doi.org/10.1109/icassp.2016.7472804","mag":"2408234571"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066545740","display_name":"Yuya Akita","orcid":"https://orcid.org/0009-0003-3036-0883"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Akita","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5875","last_page":"5879"},"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/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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.7977572083473206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.590662956237793},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5654395818710327},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.55833899974823},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5152261853218079},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5138409733772278},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4817478656768799},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47360825538635254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4572735130786896},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.44044458866119385},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4305551052093506},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42801183462142944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4236801862716675},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4107581377029419},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2815755605697632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07776686549186707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977572083473206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590662956237793},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5654395818710327},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.55833899974823},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5152261853218079},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5138409733772278},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4817478656768799},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47360825538635254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4572735130786896},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.44044458866119385},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4305551052093506},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42801183462142944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4236801862716675},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4107581377029419},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2815755605697632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07776686549186707},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728205","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930687","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W55333121","https://openalex.org/W173561343","https://openalex.org/W1505175215","https://openalex.org/W1524333225","https://openalex.org/W1571931074","https://openalex.org/W1585743408","https://openalex.org/W1606054028","https://openalex.org/W1904457459","https://openalex.org/W1975113979","https://openalex.org/W1982722627","https://openalex.org/W2009840120","https://openalex.org/W2026339097","https://openalex.org/W2033256038","https://openalex.org/W2034537249","https://openalex.org/W2047691586","https://openalex.org/W2051669046","https://openalex.org/W2095098834","https://openalex.org/W2099154261","https://openalex.org/W2124558353","https://openalex.org/W2127499922","https://openalex.org/W2133869761","https://openalex.org/W2134659216","https://openalex.org/W2136376159","https://openalex.org/W2139453310","https://openalex.org/W2147590749","https://openalex.org/W2147880316","https://openalex.org/W2151773497","https://openalex.org/W2189391786","https://openalex.org/W2250628345","https://openalex.org/W2251230323","https://openalex.org/W2261756304","https://openalex.org/W2280141299","https://openalex.org/W2295262519","https://openalex.org/W2395106899","https://openalex.org/W3208649718","https://openalex.org/W4236796448","https://openalex.org/W6607114211","https://openalex.org/W6630058488","https://openalex.org/W6631362777","https://openalex.org/W6634380342","https://openalex.org/W6657162565","https://openalex.org/W6682082992","https://openalex.org/W6687284999","https://openalex.org/W6691276412","https://openalex.org/W6697190679","https://openalex.org/W6711850222","https://openalex.org/W6803318626"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W3104108945","https://openalex.org/W2033364610","https://openalex.org/W3163689946","https://openalex.org/W2797776314","https://openalex.org/W2153927146","https://openalex.org/W2091066410","https://openalex.org/W4390190783"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"unsupervised":[3],"training":[4],"of":[5,14,39],"DNN":[6,32],"acoustic":[7,71],"model,":[8],"by":[9,28],"exploiting":[10],"a":[11,37],"large":[12],"amount":[13],"unlabeled":[15,68],"data":[16,66,69,96],"with":[17],"CRF-based":[18],"classifiers.":[19],"In":[20],"the":[21,48,53,60,81,85,91,95,100,108],"proposed":[22,75],"scheme,":[23],"we":[24],"obtain":[25],"ASR":[26,34,82],"hypotheses":[27],"complementary":[29],"GMM":[30],"and":[31,44,51,88,105],"based":[33,98],"systems.":[35],"Then,":[36],"set":[38],"dedicated":[40],"classifiers":[41,61],"are":[42],"designed":[43],"trained":[45,93],"to":[46],"select":[47],"better":[49],"hypothesis":[50],"verify":[52],"selected":[54,97],"data.":[55],"It":[56],"is":[57],"demonstrated":[58],"that":[59],"can":[62],"effectively":[63],"filter":[64],"usable":[65],"from":[67,84,94,107],"for":[70],"model":[72],"training.":[73],"The":[74],"method":[76],"achieved":[77],"significant":[78],"improvement":[79],"in":[80],"accuracy":[83],"baseline":[86],"system,":[87],"it":[89],"outperformed":[90],"models":[92],"on":[99],"confidence":[101],"measure":[102],"scores":[103],"(CMS)":[104],"also":[106],"simple":[109],"ROVER-based":[110],"system":[111],"combination.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}