{"id":"https://openalex.org/W2667408400","doi":"https://doi.org/10.1109/icassp.2017.7953162","title":"Semi-supervised ensemble DNN acoustic model training","display_name":"Semi-supervised ensemble DNN acoustic model training","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2667408400","doi":"https://doi.org/10.1109/icassp.2017.7953162","mag":"2667408400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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, Sakyoku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyoku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"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":"Shinsuke Sakai","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyoku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyoku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"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":"Masato Mimura","raw_affiliation_strings":["School of Informatics, Kyoto University, Sakyoku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyoku, 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, Sakyoku, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Kyoto University, Sakyoku, Kyoto, Japan","institution_ids":["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":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5270","last_page":"5274"},"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":0.9991000294685364,"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":0.9990000128746033,"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":0.8062494993209839},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.637000560760498},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6094192862510681},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6063903570175171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5995622873306274},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5524955987930298},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5041836500167847},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49184298515319824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4885205030441284},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48830199241638184},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4751598536968231},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.46020692586898804},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4440660774707794},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41587409377098083},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4123401939868927},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.293475866317749},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07793855667114258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062494993209839},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.637000560760498},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6094192862510681},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6063903570175171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5995622873306274},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5524955987930298},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5041836500167847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49184298515319824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4885205030441284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48830199241638184},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4751598536968231},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.46020692586898804},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4440660774707794},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41587409377098083},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4123401939868927},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.293475866317749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07793855667114258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728219","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930692","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W72347498","https://openalex.org/W330298975","https://openalex.org/W1479807131","https://openalex.org/W1524333225","https://openalex.org/W1534477342","https://openalex.org/W1762484328","https://openalex.org/W1970890968","https://openalex.org/W1978660892","https://openalex.org/W1982722627","https://openalex.org/W1989549063","https://openalex.org/W2025198378","https://openalex.org/W2033256038","https://openalex.org/W2085598899","https://openalex.org/W2104290444","https://openalex.org/W2124558353","https://openalex.org/W2134284153","https://openalex.org/W2136933783","https://openalex.org/W2139453310","https://openalex.org/W2147590749","https://openalex.org/W2189391786","https://openalex.org/W2288645994","https://openalex.org/W2289731793","https://openalex.org/W2395106899","https://openalex.org/W2402040300","https://openalex.org/W2402741009","https://openalex.org/W2404463488","https://openalex.org/W2407663967","https://openalex.org/W2430252546","https://openalex.org/W2963726581","https://openalex.org/W2997701990","https://openalex.org/W4232478844","https://openalex.org/W6602935006","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6675747103","https://openalex.org/W6680088802","https://openalex.org/W6680549991","https://openalex.org/W6687284999","https://openalex.org/W6711850222","https://openalex.org/W6712807034","https://openalex.org/W6712847557","https://openalex.org/W6713921840"],"related_works":["https://openalex.org/W4317548404","https://openalex.org/W3022007134","https://openalex.org/W2130553454","https://openalex.org/W2087783760","https://openalex.org/W2033364610","https://openalex.org/W2797776314","https://openalex.org/W3163689946","https://openalex.org/W2153927146","https://openalex.org/W3104108945","https://openalex.org/W4390190783"],"abstract_inverted_index":{"It":[0],"is":[1],"very":[2],"important":[3],"to":[4,28,31,55,69],"exploit":[5],"abundant":[6],"unlabeled":[7,24,71],"speech":[8,17],"for":[9,118],"improving":[10],"the":[11,33,39,57,70,91,94,102,105,110],"acoustic":[12,87],"model":[13,34,58,100],"training":[14,21,45,81],"in":[15,26,104],"automatic":[16],"recognition":[18],"(ASR).":[19],"Semi-supervised":[20],"methods":[22],"incorporate":[23],"data":[25,30],"addition":[27],"labeled":[29],"enhance":[32],"training,":[35],"but":[36,63],"it":[37,64],"encounters":[38],"error-prone":[40],"label":[41],"problem.":[42],"The":[43,98],"ensemble":[44,95],"scheme":[46],"trains":[47],"a":[48,116],"set":[49],"of":[50,82,96],"models":[51,88],"and":[52,61],"combines":[53],"them":[54],"make":[56],"more":[59],"general":[60],"robust,":[62],"has":[65,113],"not":[66],"been":[67],"applied":[68],"data.":[72],"In":[73],"this":[74],"work,":[75],"we":[76],"propose":[77],"an":[78],"effective":[79],"semi-supervised":[80],"deep":[83],"neural":[84],"network":[85],"(DNN)":[86],"by":[89],"incorporating":[90],"diversity":[92],"among":[93],"models.":[97],"resultant":[99],"improved":[101],"performance":[103],"lecture":[106],"transcription":[107],"task.":[108],"Moreover,":[109],"proposed":[111],"method":[112],"also":[114],"shown":[115],"potential":[117],"DNN":[119],"adaptation.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}