{"id":"https://openalex.org/W2787322890","doi":"https://doi.org/10.1109/apsipa.2017.8282123","title":"Speech emotion recognition based on multi-task learning using a convolutional neural network","display_name":"Speech emotion recognition based on multi-task learning using a convolutional neural network","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787322890","doi":"https://doi.org/10.1109/apsipa.2017.8282123","mag":"2787322890"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5067154795","display_name":"Nam Kyun Kim","orcid":"https://orcid.org/0000-0001-6923-230X"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Nam Kyun Kim","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048468979","display_name":"Ji\u2010Won Lee","orcid":"https://orcid.org/0000-0002-2666-4249"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiwon Lee","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082089314","display_name":"Hun Kyu Ha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hun Kyu Ha","raw_affiliation_strings":["Artificial Intelligence Engine Laboratory, Acryl, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Engine Laboratory, Acryl, Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028537246","display_name":"Geon Woo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geon Woo Lee","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062121707","display_name":"Jung Hyuk Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Hyuk Lee","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067154795"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":null,"apc_paid":null,"fwci":1.3057,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.82174349,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"707"},"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":0.9997000098228455,"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":0.9995999932289124,"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":0.7584996223449707},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7327173352241516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6765207648277283},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6321945190429688},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6287710070610046},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.58432537317276},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5476866364479065},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5372127890586853},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5272678136825562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4897341728210449},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4432607889175415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43618106842041016},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4213974177837372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584996223449707},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7327173352241516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6765207648277283},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6321945190429688},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6287710070610046},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.58432537317276},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5476866364479065},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5372127890586853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5272678136825562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4897341728210449},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4432607889175415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43618106842041016},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4213974177837372},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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:10.1109/apsipa.2017.8282123","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1522301498","https://openalex.org/W1972280480","https://openalex.org/W1974924514","https://openalex.org/W2025401819","https://openalex.org/W2032254851","https://openalex.org/W2045757585","https://openalex.org/W2059372649","https://openalex.org/W2074788634","https://openalex.org/W2094035326","https://openalex.org/W2095705004","https://openalex.org/W2102697000","https://openalex.org/W2110052520","https://openalex.org/W2119417805","https://openalex.org/W2149628368","https://openalex.org/W2160815625","https://openalex.org/W2271840356","https://openalex.org/W2578895956","https://openalex.org/W2757445263","https://openalex.org/W2913340405","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6676494506","https://openalex.org/W6677944028","https://openalex.org/W7048126131"],"related_works":["https://openalex.org/W3183901164","https://openalex.org/W2951211570","https://openalex.org/W3135818718","https://openalex.org/W4290188444","https://openalex.org/W3003905048","https://openalex.org/W2253429366","https://openalex.org/W3127975138","https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864"],"abstract_inverted_index":{"In":[0,71],"this":[1,59],"paper,":[2],"we":[3],"propose":[4],"a":[5,12,48,131,138,141,153],"speech":[6,146],"emotion":[7,98,155],"recognition":[8,156],"(SER)":[9],"method":[10,63],"with":[11,101,148,152],"multi-task":[13,65],"learning-based":[14],"convolutional":[15,77],"neural":[16,28,78],"network":[17,79],"(MTL-CNN).":[18],"It":[19,116],"has":[20],"been":[21],"recently":[22],"reported":[23],"that":[24,122],"classifiers":[25,45],"using":[26,126,149],"deep":[27],"networks":[29],"(DNNs)":[30],"outperformed":[31],"the":[32,61,74,82,96,106,112,127,150],"hidden":[33],"Markov":[34],"model":[35],"(HMM)":[36],"and":[37,89,111],"support":[38],"vector":[39],"machine":[40],"(SVM).":[41],"However,":[42],"such":[43],"DNN-based":[44],"still":[46],"have":[47],"generalization":[49],"error":[50],"problem":[51],"due":[52],"to":[53],"limited":[54],"training":[55],"data.":[56],"To":[57],"mitigate":[58],"problem,":[60],"proposed":[62,75,128],"incorporates":[64],"learning":[66],"(MTL)":[67],"as":[68,91],"transfer":[69],"learning.":[70],"other":[72],"words,":[73],"MTL-based":[76],"(MTL-CNN)":[80],"contains":[81],"classification":[83,99],"of":[84,135,144],"arousal":[85],"level,":[86,88],"valence":[87],"gender":[90],"three":[92,102],"auxiliary":[93,103],"tasks.":[94,115],"Training":[95],"main":[97],"task":[100,139],"tasks":[104],"helps":[105],"MTL-CNN":[107,129],"learn":[108],"useful":[109],"features":[110],"relationships":[113],"between":[114],"is":[117],"demonstrated":[118],"through":[119],"SER":[120,124],"experiments":[121],"an":[123],"system":[125],"achieves":[130],"relative":[132],"F1-score":[133],"improvement":[134],"3.64%":[136],"for":[137],"on":[140],"Berlin":[142],"database":[143],"emotional":[145],"compared":[147],"CNN":[151],"single":[154],"task.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}