{"id":"https://openalex.org/W2964128364","doi":"https://doi.org/10.21437/interspeech.2017-736","title":"Towards Speech Emotion Recognition \u201cin the Wild\u201d Using Aggregated Corpora and Deep Multi-Task Learning","display_name":"Towards Speech Emotion Recognition \u201cin the Wild\u201d Using Aggregated Corpora and Deep Multi-Task Learning","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2964128364","doi":"https://doi.org/10.21437/interspeech.2017-736","mag":"2964128364"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-736","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"preprint","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/A5010496535","display_name":"Jaebok Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaebok Kim","raw_affiliation_strings":["Human Media Interaction, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Media Interaction, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074888054","display_name":"Gwenn Englebienne","orcid":"https://orcid.org/0000-0002-3130-2082"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gwenn Englebienne","raw_affiliation_strings":["Human Media Interaction, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Media Interaction, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068294985","display_name":"Khiet P. Truong","orcid":"https://orcid.org/0000-0002-7243-0523"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Khiet P. Truong","raw_affiliation_strings":["Human Media Interaction, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Media Interaction, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077237173","display_name":"Vanessa Evers","orcid":"https://orcid.org/0000-0002-5650-2830"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vanessa Evers","raw_affiliation_strings":["Human Media Interaction, University of Twente, Enschede, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Media Interaction, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6092,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.97344861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1113","last_page":"1117"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9927999973297119,"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":0.9927999973297119,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9918000102043152,"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/T10860","display_name":"Speech and Audio Processing","score":0.9782999753952026,"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":0.7884271740913391},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7014702558517456},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6764297485351562},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6684762239456177},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5504169464111328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477173328399658},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.44913449883461},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4388417899608612},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42990541458129883},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30303889513015747},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05826631188392639}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884271740913391},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7014702558517456},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6764297485351562},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6684762239456177},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5504169464111328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477173328399658},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.44913449883461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388417899608612},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42990541458129883},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30303889513015747},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05826631188392639},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-736","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W175750906","https://openalex.org/W1522301498","https://openalex.org/W1581984155","https://openalex.org/W1896424170","https://openalex.org/W1993882792","https://openalex.org/W2016043834","https://openalex.org/W2016839396","https://openalex.org/W2024289965","https://openalex.org/W2047380481","https://openalex.org/W2095705004","https://openalex.org/W2099215977","https://openalex.org/W2125462608","https://openalex.org/W2135195345","https://openalex.org/W2137639365","https://openalex.org/W2146334809","https://openalex.org/W2163922914","https://openalex.org/W2165644552","https://openalex.org/W2187089797","https://openalex.org/W2295001676","https://openalex.org/W2337753992","https://openalex.org/W2399733683","https://openalex.org/W2400814905","https://openalex.org/W2408520939","https://openalex.org/W2752818578","https://openalex.org/W2963131709","https://openalex.org/W3104240813","https://openalex.org/W3209042722","https://openalex.org/W4300633279"],"related_works":["https://openalex.org/W2773616286","https://openalex.org/W2810519502","https://openalex.org/W2785763105","https://openalex.org/W2012919372","https://openalex.org/W2572592660","https://openalex.org/W2072215176","https://openalex.org/W2541962547","https://openalex.org/W1923358586","https://openalex.org/W3095578185","https://openalex.org/W2120845695"],"abstract_inverted_index":{"One":[0],"of":[1,30,76,115],"the":[2,10,13,27,31,67,77,112,116],"challenges":[3],"in":[4,49,56,111],"Speech":[5],"Emotion":[6],"Recognition":[7],"(SER)":[8],"\"in":[9,66],"wild\"":[11],"is":[12],"large":[14],"mismatch":[15],"between":[16],"training":[17],"and":[18,22,41,44,58,94],"test":[19],"data":[20],"(e.g.speakers":[21],"tasks).In":[23],"order":[24],"to":[25,36,70],"improve":[26],"generalisation":[28],"capabilities":[29],"emotion":[32],"models,":[33],"we":[34,80],"propose":[35],"use":[37,42],"Multi-Task":[38],"Learning":[39,72],"(MTL)":[40],"gender":[43,93,103],"naturalness":[45,95,105],"as":[46],"auxiliary":[47],"tasks":[48],"deep":[50],"neural":[51],"networks.This":[52],"method":[53,85,122],"was":[54,108],"evaluated":[55],"within-corpus":[57],"various":[59],"cross-corpus":[60],"classification":[61],"experiments":[62],"that":[63,82],"simulate":[64],"conditions":[65],"wild\".In":[68],"comparison":[69],"Single-Task":[71],"(STL)":[73],"based":[74],"state":[75],"art":[78],"methods,":[79],"found":[81,110],"our":[83,121],"MTL":[84],"proposed":[86],"improved":[87],"performance":[88],"significantly.Particularly,":[89],"models":[90],"using":[91,101],"both":[92],"achieved":[96],"more":[97],"gains":[98],"than":[99],"those":[100],"either":[102],"or":[104],"separately.This":[106],"benefit":[107],"also":[109],"high-level":[113],"representations":[114],"feature":[117],"space,":[118],"obtained":[119],"from":[120],"proposed,":[123],"where":[124],"discriminative":[125],"emotional":[126],"clusters":[127],"could":[128],"be":[129],"observed.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}