{"id":"https://openalex.org/W3117814038","doi":"https://doi.org/10.23919/eusipco47968.2020.9287484","title":"An End-to-end Multitask Learning Model to Improve Speech Emotion Recognition","display_name":"An End-to-end Multitask Learning Model to Improve Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3117814038","doi":"https://doi.org/10.23919/eusipco47968.2020.9287484","mag":"3117814038"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287484","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5085633547","display_name":"Changzeng Fu","orcid":"https://orcid.org/0000-0003-1083-9486"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Changzeng Fu","raw_affiliation_strings":["Advanced Telecommunications Research Institute International, Japan","Graduate School of Engineering Science, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905297","display_name":"Chaoran Liu","orcid":"https://orcid.org/0000-0003-3789-2981"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":["Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Carlos Toshinori Ishi","raw_affiliation_strings":["Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Advanced Telecommunications Research Institute International, Japan","Graduate School of Engineering Science, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9970999956130981,"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":0.804312527179718},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6738321185112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6728241443634033},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6383411288261414},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6227190494537354},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6053518652915955},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5378714203834534},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5256468057632446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4977765381336212},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4786011874675751},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4628564119338989},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45624297857284546},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4389435052871704},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.42016923427581787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34386247396469116}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804312527179718},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6738321185112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6728241443634033},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6383411288261414},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6227190494537354},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6053518652915955},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5378714203834534},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5256468057632446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4977765381336212},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4786011874675751},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4628564119338989},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45624297857284546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4389435052871704},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.42016923427581787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34386247396469116},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287484","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287484","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1501669607","https://openalex.org/W2037441721","https://openalex.org/W2097888244","https://openalex.org/W2144005487","https://openalex.org/W2171948352","https://openalex.org/W2552839021","https://openalex.org/W2567070169","https://openalex.org/W2625297138","https://openalex.org/W2766756589","https://openalex.org/W2787369546","https://openalex.org/W2889191349","https://openalex.org/W2889286050","https://openalex.org/W2937977583","https://openalex.org/W2939224318","https://openalex.org/W2959133507","https://openalex.org/W2963970792","https://openalex.org/W2970764359","https://openalex.org/W2972495317","https://openalex.org/W3104980021","https://openalex.org/W6607193717","https://openalex.org/W6630073874","https://openalex.org/W6681409903","https://openalex.org/W6730218677","https://openalex.org/W6731370813","https://openalex.org/W6761808342"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W2916997151","https://openalex.org/W1923358586","https://openalex.org/W2949174760","https://openalex.org/W4283754361","https://openalex.org/W3042022268"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,28,62,81],"propose":[4],"an":[5,67],"attention-based":[6],"CNN-BLSTM":[7],"model":[8,38,113],"with":[9,101,135],"the":[10,37,47,72,92,125,133],"end-to-end":[11],"(E2E)":[12],"learning":[13],"method.":[14],"We":[15,90],"first":[16],"extract":[17],"Mel-spectrogram":[18],"from":[19,84],"wav":[20],"file":[21],"instead":[22],"of":[23,32,43,127],"using":[24],"handcrafted":[25],"features.":[26],"Then":[27],"adopt":[29],"two":[30],"types":[31],"attention":[33],"mechanisms":[34],"to":[35],"let":[36],"focuses":[39],"on":[40,95],"salient":[41],"periods":[42],"speech":[44,128],"emotions":[45],"over":[46],"temporal":[48],"dimension.":[49],"Considering":[50],"that":[51,110],"there":[52],"are":[53],"many":[54],"individual":[55],"differences":[56],"among":[57],"people":[58],"in":[59,124],"expressing":[60],"emotions,":[61],"incorporate":[63],"speaker":[64],"recognition":[65],"as":[66,87],"auxiliary":[68],"task.":[69],"Moreover,":[70],"since":[71],"training":[73,99],"data":[74,83,88],"set":[75],"has":[76],"a":[77],"small":[78],"sample":[79],"size,":[80],"include":[82],"another":[85],"language":[86],"augmentation.":[89],"evaluated":[91],"proposed":[93,112],"method":[94],"SAVEE":[96],"dataset":[97],"by":[98],"it":[100],"single":[102],"task,":[103],"multitask,":[104],"and":[105,119],"cross-language.":[106],"The":[107],"evaluation":[108],"shows":[109],"our":[111],"achieves":[114],"73.62%":[115],"for":[116,121],"weighted":[117],"accuracy":[118,123],"71.11%":[120],"un-weighted":[122],"task":[126],"emotion":[129],"recognition,":[130],"which":[131],"outperforms":[132],"baseline":[134],"11.13":[136],"points.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}