{"id":"https://openalex.org/W4392281383","doi":"https://doi.org/10.1587/transinf.2023hcp0010","title":"Simultaneous Adaptation of Acoustic and Language Models for Emotional Speech Recognition Using Tweet Data","display_name":"Simultaneous Adaptation of Acoustic and Language Models for Emotional Speech Recognition Using Tweet Data","publication_year":2024,"publication_date":"2024-02-29","ids":{"openalex":"https://openalex.org/W4392281383","doi":"https://doi.org/10.1587/transinf.2023hcp0010"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2023hcp0010","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023hcp0010","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/3/E107.D_2023HCP0010/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/3/E107.D_2023HCP0010/_pdf","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/I4210165438","display_name":"Yamagata University Hospital","ror":"https://ror.org/05gg4qm19","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210165438"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo KOSAKA","raw_affiliation_strings":["Yamagata University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University","institution_ids":["https://openalex.org/I4210165438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032204910","display_name":"Kazuya Saeki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165438","display_name":"Yamagata University Hospital","ror":"https://ror.org/05gg4qm19","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210165438"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya SAEKI","raw_affiliation_strings":["Yamagata University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University","institution_ids":["https://openalex.org/I4210165438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010360981","display_name":"Yoshitaka Aizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165438","display_name":"Yamagata University Hospital","ror":"https://ror.org/05gg4qm19","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210165438"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshitaka AIZAWA","raw_affiliation_strings":["Yamagata University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University","institution_ids":["https://openalex.org/I4210165438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111137741","display_name":"Kato Masaharu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165438","display_name":"Yamagata University Hospital","ror":"https://ror.org/05gg4qm19","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210165438"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaharu KATO","raw_affiliation_strings":["Yamagata University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University","institution_ids":["https://openalex.org/I4210165438"]}]},{"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":["Tohoku University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University","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":0.8335,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75205359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"E107.D","issue":"3","first_page":"363","last_page":"373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9987000226974487,"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":0.9987000226974487,"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":0.8086923956871033},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7274885177612305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6987489461898804},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6919043064117432},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5497052669525146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48981186747550964},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.486594557762146},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.4621162712574005},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4409920573234558},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4232312738895416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38974976539611816},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3337370753288269},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2854369282722473},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.1604229211807251},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1419212520122528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086923956871033},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7274885177612305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6987489461898804},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6919043064117432},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5497052669525146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48981186747550964},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.486594557762146},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.4621162712574005},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4409920573234558},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4232312738895416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38974976539611816},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3337370753288269},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2854369282722473},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.1604229211807251},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1419212520122528},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2023hcp0010","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023hcp0010","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/3/E107.D_2023HCP0010/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2023hcp0010","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2023hcp0010","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/3/E107.D_2023HCP0010/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1984533313","display_name":"Development of emotion recognition system by transfer learning for various speeches","funder_award_id":"22K12087","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7398910974","display_name":"Emotion detection from speech using high-accuracy emotional speech recognition","funder_award_id":"19K12014","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392281383.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W165283731","https://openalex.org/W175750906","https://openalex.org/W1970362344","https://openalex.org/W2024672690","https://openalex.org/W2052488007","https://openalex.org/W2056890665","https://openalex.org/W2087779800","https://openalex.org/W2097377227","https://openalex.org/W2403841285","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/W2786756662","https://openalex.org/W2889332211","https://openalex.org/W2921306346","https://openalex.org/W2963295373","https://openalex.org/W2975911382","https://openalex.org/W2985294889","https://openalex.org/W3009578392","https://openalex.org/W3034729383","https://openalex.org/W3130670035","https://openalex.org/W3195321095","https://openalex.org/W4200018452","https://openalex.org/W4320498290"],"related_works":["https://openalex.org/W2129812225","https://openalex.org/W2611868346","https://openalex.org/W3081187864","https://openalex.org/W2803306015","https://openalex.org/W2784059283","https://openalex.org/W4380605396","https://openalex.org/W2291624303","https://openalex.org/W2105439218","https://openalex.org/W2948132774","https://openalex.org/W2141404479"],"abstract_inverted_index":{"Emotional":[0,73],"speech":[1,10,17,79],"recognition":[2,58,169],"is":[3,97,116],"generally":[4],"considered":[5],"more":[6],"difficult":[7],"than":[8],"non-emotional":[9,22],"recognition.":[11],"The":[12,139,189],"acoustic":[13,25,62,182],"characteristics":[14,26],"of":[15,21,35,84,113,126,158,194],"emotional":[16,40,67,78,89],"differ":[18],"from":[19,136,146],"those":[20],"speech.":[23,68],"Additionally,":[24],"vary":[27],"significantly":[28],"depending":[29],"on":[30,151],"the":[31,100,108,111,127,137,147,156,168,171,181,192,195],"type":[32],"and":[33,41,63,86,162,183],"intensity":[34],"emotions.":[36],"Regarding":[37],"linguistic":[38],"features,":[39],"colloquial":[42],"expressions":[43],"are":[44],"also":[45],"observed":[46],"in":[47,103],"their":[48],"utterances.":[49],"To":[50,118],"solve":[51,119],"these":[52],"problems,":[53],"we":[54,122],"aim":[55],"to":[56,66,92],"improve":[57],"performance":[59],"by":[60,130],"adapting":[61],"language":[64,109,128,184],"models":[65],"We":[69,154],"used":[70,141,163],"Japanese":[71],"Twitter-based":[72],"Speech":[74],"(JTES)":[75],"as":[76],"an":[77,88,124],"corpus.":[80,105],"This":[81],"corpus":[82],"consisted":[83],"tweets":[85],"had":[87],"label":[90],"assigned":[91],"each":[93],"utterance.":[94],"Corpus":[95],"adaptation":[96,114,125,143,186],"possible":[98],"using":[99,131],"utterances":[101],"contained":[102],"this":[104,120],"However,":[106],"regarding":[107],"model,":[110],"amount":[112],"data":[115,134,149,157],"insufficient.":[117],"problem,":[121],"propose":[123],"model":[129,185],"online":[132],"tweet":[133,148],"downloaded":[135],"internet.":[138],"sentences":[140],"for":[142,165],"were":[144],"extracted":[145,155],"based":[150],"certain":[152],"rules.":[153],"25.86":[159],"M":[160],"words":[161],"them":[164],"adaptation.":[166],"In":[167],"experiments,":[170],"baseline":[172],"word":[173],"error":[174],"rate":[175],"was":[176,187],"36.11%,":[177],"whereas":[178],"that":[179],"with":[180],"17.77%.":[188],"results":[190],"demonstrated":[191],"effectiveness":[193],"proposed":[196],"method.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2025-10-10T00:00:00"}