{"id":"https://openalex.org/W2921306346","doi":"https://doi.org/10.23919/apsipa.2018.8659756","title":"Acoustic Model Adaptation for Emotional Speech Recognition Using Twitter-Based Emotional Speech Corpus","display_name":"Acoustic Model Adaptation for Emotional Speech Recognition Using Twitter-Based Emotional Speech Corpus","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921306346","doi":"https://doi.org/10.23919/apsipa.2018.8659756","mag":"2921306346"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659756","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5112342909","display_name":"Tetsuo Kosaka","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo Kosaka","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010360981","display_name":"Yoshitaka Aizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshitaka Aizawa","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101139126","display_name":"Masaharu Kato","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaharu Kato","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4527,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69044155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1747","last_page":"1751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9983000159263611,"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":0.9957000017166138,"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/speech-recognition","display_name":"Speech recognition","score":0.7135056853294373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6638306975364685},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5949985384941101},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.457495778799057},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4352126717567444},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42811036109924316},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42112329602241516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4012815058231354},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36379125714302063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3452928364276886},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.29402291774749756},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2733023166656494}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7135056853294373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6638306975364685},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5949985384941101},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.457495778799057},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4352126717567444},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42811036109924316},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42112329602241516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4012815058231354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36379125714302063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3452928364276886},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29402291774749756},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2733023166656494},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659756","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5916684090","display_name":"A study on acoustic model adaptation for deep-learning-based speech recognition","funder_award_id":"16K00227","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W175750906","https://openalex.org/W1601795611","https://openalex.org/W1970362344","https://openalex.org/W1985371235","https://openalex.org/W1993409002","https://openalex.org/W2024672690","https://openalex.org/W2056738732","https://openalex.org/W2087779800","https://openalex.org/W2293634267","https://openalex.org/W2403841285","https://openalex.org/W2508162385","https://openalex.org/W2515233083","https://openalex.org/W2584245668","https://openalex.org/W2611652970","https://openalex.org/W2745949735","https://openalex.org/W2749891261","https://openalex.org/W2781366654","https://openalex.org/W2963295373","https://openalex.org/W3034729383","https://openalex.org/W6607193717","https://openalex.org/W6640373744","https://openalex.org/W6696934422","https://openalex.org/W6713272703","https://openalex.org/W6732761015","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W4388820305","https://openalex.org/W4298261218","https://openalex.org/W3151376046","https://openalex.org/W430347950","https://openalex.org/W2992378684","https://openalex.org/W2147998355","https://openalex.org/W3169479349","https://openalex.org/W1987021544","https://openalex.org/W2105439218"],"abstract_inverted_index":{"In":[0,58,128],"recent":[1],"years,":[2],"Japanese":[3],"Twitter-based":[4],"emotional":[5,12,26,51,68],"speech":[6,13,47,52,69],"(JTES)":[7],"was":[8,105,110,120,141,148],"constructed":[9],"as":[10,91,122],"an":[11,25,123],"corpus.":[14],"This":[15,118],"corpus":[16,74,114],"is":[17,28,54,89],"based":[18],"on":[19,71],"tweets,":[20],"and":[21,33,43,137],"has":[22],"features":[23],"wherein":[24],"label":[27],"assigned":[29],"to":[30,46,63],"each":[31],"sentence,":[32],"sentences":[34],"are":[35],"selected":[36],"considering":[37],"the":[38,65,72,92,108,113],"balance":[39],"of":[40,67,103,115,133,146],"both":[41],"phoneme":[42],"prosody.":[44],"Compared":[45],"recognition":[48,53,70],"without":[49],"emotion,":[50],"a":[55,81,96,98,144],"difficult":[56],"task.":[57],"this":[59,129],"study,":[60,130],"we":[61],"aim":[62],"improve":[64],"performance":[66,139],"JTES":[73],"using":[75,150],"acoustic":[76,93],"model":[77,87,119,125],"adaptation.":[78,127,152],"For":[79],"recognition,":[80],"deep":[82],"neural":[83],"network-based":[84],"hidden":[85],"Markov":[86],"(DNN-HMM)":[88],"used":[90,121],"model.":[94],"As":[95],"baseline,":[97],"word":[99],"error":[100],"rate":[101],"(WER)":[102],"38.0%":[104],"obtained":[106,149],"when":[107],"DNN-HMM":[109],"trained":[111],"by":[112],"spontaneous":[116],"Japanese.":[117],"initial":[124],"for":[126],"various":[131],"types":[132],"adaptation":[134],"were":[135],"examined,":[136],"substantial":[138],"improvement":[140],"achieved.":[142],"Finally,":[143],"WER":[145],"23.05%":[147],"speaker":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}