{"id":"https://openalex.org/W2430252546","doi":"https://doi.org/10.1109/taslp.2016.2562505","title":"Semi-Supervised Acoustic Model Training by Discriminative Data Selection From Multiple ASR Systems\u2019 Hypotheses","display_name":"Semi-Supervised Acoustic Model Training by Discriminative Data Selection From Multiple ASR Systems\u2019 Hypotheses","publication_year":2016,"publication_date":"2016-05-03","ids":{"openalex":"https://openalex.org/W2430252546","doi":"https://doi.org/10.1109/taslp.2016.2562505","mag":"2430252546"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2562505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2562505","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/219417","any_repository_has_fulltext":true},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7636-3797","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuya Akita","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5008,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90027784,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"24","issue":"9","first_page":"1524","last_page":"1534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/discriminative-model","display_name":"Discriminative model","score":0.8029789328575134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7711870074272156},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6001808047294617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5986325740814209},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5894648432731628},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5238338112831116},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5172486901283264},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.4599766731262207},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45898282527923584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45318764448165894},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41010159254074097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38309505581855774}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8029789328575134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7711870074272156},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6001808047294617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986325740814209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5894648432731628},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5238338112831116},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5172486901283264},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.4599766731262207},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45898282527923584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45318764448165894},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41010159254074097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38309505581855774},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2016.2562505","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2562505","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000175119","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/219417","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728062","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930633","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":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000175119","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/219417","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7388475868","display_name":"Automatic speech recognition based on semi-autonomous learning for captioning lectures","funder_award_id":"16H02847","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W34303869","https://openalex.org/W44815768","https://openalex.org/W55333121","https://openalex.org/W65139299","https://openalex.org/W72347498","https://openalex.org/W173561343","https://openalex.org/W201749652","https://openalex.org/W1498436455","https://openalex.org/W1501286448","https://openalex.org/W1505175215","https://openalex.org/W1524333225","https://openalex.org/W1571931074","https://openalex.org/W1585743408","https://openalex.org/W1606054028","https://openalex.org/W1608381367","https://openalex.org/W1904457459","https://openalex.org/W1970890968","https://openalex.org/W1975113979","https://openalex.org/W1978660892","https://openalex.org/W1982722627","https://openalex.org/W1984985727","https://openalex.org/W1987238397","https://openalex.org/W1993660824","https://openalex.org/W1993666847","https://openalex.org/W2009840120","https://openalex.org/W2012419652","https://openalex.org/W2025198378","https://openalex.org/W2026339097","https://openalex.org/W2033256038","https://openalex.org/W2034537249","https://openalex.org/W2047691586","https://openalex.org/W2051669046","https://openalex.org/W2070737455","https://openalex.org/W2084294137","https://openalex.org/W2085598899","https://openalex.org/W2095098834","https://openalex.org/W2099154261","https://openalex.org/W2124558353","https://openalex.org/W2127499922","https://openalex.org/W2131342762","https://openalex.org/W2133869761","https://openalex.org/W2134659216","https://openalex.org/W2136376159","https://openalex.org/W2136922672","https://openalex.org/W2139453310","https://openalex.org/W2145077480","https://openalex.org/W2147590749","https://openalex.org/W2147768505","https://openalex.org/W2147880316","https://openalex.org/W2151773497","https://openalex.org/W2159391028","https://openalex.org/W2159748844","https://openalex.org/W2166697331","https://openalex.org/W2169384404","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/W2396659748","https://openalex.org/W2402741009","https://openalex.org/W2404463488","https://openalex.org/W3034729383","https://openalex.org/W3208649718","https://openalex.org/W4236796448","https://openalex.org/W6601375071","https://openalex.org/W6601785968","https://openalex.org/W6602268766","https://openalex.org/W6602743316","https://openalex.org/W6602935006","https://openalex.org/W6607114211","https://openalex.org/W6608203040","https://openalex.org/W6630058488","https://openalex.org/W6630162575","https://openalex.org/W6631362777","https://openalex.org/W6634380342","https://openalex.org/W6636107938","https://openalex.org/W6636499491","https://openalex.org/W6657162565","https://openalex.org/W6674740853","https://openalex.org/W6679429981","https://openalex.org/W6682082992","https://openalex.org/W6684930139","https://openalex.org/W6691276412","https://openalex.org/W6694765965","https://openalex.org/W6697190679","https://openalex.org/W6711850222","https://openalex.org/W6712446967","https://openalex.org/W6712807034","https://openalex.org/W6713140504","https://openalex.org/W6779469704","https://openalex.org/W6803318626"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W3172695526","https://openalex.org/W2786391746","https://openalex.org/W2991483587","https://openalex.org/W4381430104","https://openalex.org/W2995102745","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W1990237101","https://openalex.org/W3196471634"],"abstract_inverted_index":{"While":[0],"the":[1,8,11,35,47,55,79,84,96,105,127,133,140,144],"performance":[2],"of":[3,10,37,40,72],"ASR":[4,60,67,128],"systems":[5],"depends":[6],"on":[7,110],"size":[9],"training":[12,31],"data,":[13],"it":[14],"is":[15,75,116,130],"very":[16],"costly":[17],"to":[18,77],"prepare":[19],"accurate":[20],"and":[21,65,82,136,148],"faithful":[22],"transcripts.":[23],"In":[24,54],"this":[25],"paper,":[26],"we":[27,58],"investigate":[28],"a":[29,70],"semisupervised":[30],"scheme,":[32],"which":[33],"takes":[34],"advantage":[36],"huge":[38],"quantities":[39],"unlabeled":[41],"video":[42],"lecture":[43],"archive,":[44],"particularly":[45],"for":[46,120],"deep":[48],"neural":[49],"network":[50],"(DNN)":[51],"acoustic":[52],"model.":[53],"proposed":[56,88],"method,":[57],"obtain":[59],"hypotheses":[61,81],"by":[62],"complementary":[63],"GMM-":[64],"DNN-based":[66],"systems.":[68],"Then,":[69],"set":[71],"CRF-based":[73],"classifiers":[74],"trained":[76,142],"select":[78],"correct":[80],"verify":[83],"selected":[85],"data.":[86,123],"The":[87],"hypothesis":[89],"combination":[90,99,147],"shows":[91],"higher":[92],"quality":[93],"compared":[94,103],"with":[95,104,139,143],"conventional":[97,106,145],"system":[98,135,146],"method":[100,115],"(ROVER).":[101],"Moreover,":[102],"data":[107,149],"selection":[108,150],"based":[109],"confidence":[111],"measure":[112],"score,":[113],"our":[114],"demonstrated":[117],"more":[118],"effective":[119],"filtering":[121],"usable":[122],"Significant":[124],"improvement":[125],"in":[126,137],"accuracy":[129],"achieved":[131],"over":[132],"baseline":[134],"comparison":[138],"models":[141],"methods.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}