{"id":"https://openalex.org/W3096615741","doi":"https://doi.org/10.21437/interspeech.2020-1356","title":"Speech Emotion Recognition \u2018in the Wild\u2019 Using an Autoencoder","display_name":"Speech Emotion Recognition \u2018in the Wild\u2019 Using an Autoencoder","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096615741","doi":"https://doi.org/10.21437/interspeech.2020-1356","mag":"3096615741"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5057202580","display_name":"Vipula Dissanayake","orcid":"https://orcid.org/0000-0002-2584-7318"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I4210145583","display_name":"Bioengineering Center","ror":"https://ror.org/04f0ydx59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145583"]}],"countries":["NZ","RU"],"is_corresponding":false,"raw_author_name":"Vipula Dissanayake","raw_affiliation_strings":["Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I4210145583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025564359","display_name":"Haimo Zhang","orcid":"https://orcid.org/0000-0001-8915-0360"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I4210145583","display_name":"Bioengineering Center","ror":"https://ror.org/04f0ydx59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145583"]}],"countries":["NZ","RU"],"is_corresponding":false,"raw_author_name":"Haimo Zhang","raw_affiliation_strings":["Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I4210145583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021195349","display_name":"Mark Billinghurst","orcid":"https://orcid.org/0000-0003-4172-6759"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Mark Billinghurst","raw_affiliation_strings":["Empathic Computing Lab, Auckland Bioengineering Institute, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Empathic Computing Lab, Auckland Bioengineering Institute, The University of Auckland","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027647989","display_name":"Suranga Nanayakkara","orcid":"https://orcid.org/0000-0001-7441-5493"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I4210145583","display_name":"Bioengineering Center","ror":"https://ror.org/04f0ydx59","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210145583"]}],"countries":["NZ","RU"],"is_corresponding":false,"raw_author_name":"Suranga Nanayakkara","raw_affiliation_strings":["Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augmented Human Lab, Auckland Bioengineering Institute, The University of Auckland","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I4210145583"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"526","last_page":"530"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8688806891441345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7826989889144897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6479450464248657},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5636573433876038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44778335094451904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3939124643802643},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19140928983688354}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8688806891441345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7826989889144897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479450464248657},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5636573433876038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44778335094451904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3939124643802643},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19140928983688354}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1356","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/59694","is_oa":false,"landing_page_url":"https://hdl.handle.net/2292/59694","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W283543405","https://openalex.org/W589698015","https://openalex.org/W1491064235","https://openalex.org/W1522301498","https://openalex.org/W2074788634","https://openalex.org/W2110052520","https://openalex.org/W2111926505","https://openalex.org/W2119417805","https://openalex.org/W2146334809","https://openalex.org/W2181347294","https://openalex.org/W2186450909","https://openalex.org/W2187089797","https://openalex.org/W2397175282","https://openalex.org/W2614874155","https://openalex.org/W2726515241","https://openalex.org/W2747172199","https://openalex.org/W2761514455","https://openalex.org/W2785044468","https://openalex.org/W2795986449","https://openalex.org/W2803098682","https://openalex.org/W2803193013","https://openalex.org/W2883409523","https://openalex.org/W2889090126","https://openalex.org/W2914132458","https://openalex.org/W2936173226","https://openalex.org/W2951442257","https://openalex.org/W2963087613","https://openalex.org/W2964121744","https://openalex.org/W2964128364","https://openalex.org/W2969889150","https://openalex.org/W2972691009","https://openalex.org/W2972724712","https://openalex.org/W2972852081","https://openalex.org/W3035219538","https://openalex.org/W3109943296","https://openalex.org/W4213192516","https://openalex.org/W4239447739"],"related_works":["https://openalex.org/W4287995534","https://openalex.org/W2998168123","https://openalex.org/W4220775285","https://openalex.org/W2776466379","https://openalex.org/W2897995864","https://openalex.org/W2572600474","https://openalex.org/W2592385986","https://openalex.org/W2785535669","https://openalex.org/W3090006671","https://openalex.org/W2966657595"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"has":[4,34],"been":[5,13,24,35],"a":[6,75,79,101,160],"challenging":[7],"task":[8],"on":[9,113],"which":[10],"researchers":[11],"have":[12,23],"working":[14],"for":[15],"decades.":[16],"Recently,":[17],"Deep":[18],"Learning":[19],"(DL)":[20],"based":[21,70,157,172,186,194],"approaches":[22],"shown":[25],"to":[26,43,50,64,100,135],"perform":[27],"well":[28],"in":[29,129],"SER":[30,71,195],"tasks;":[31],"however,":[32],"it":[33],"noticed":[36],"that":[37,169],"their":[38],"superior":[39],"performance":[40,149],"is":[41,95,111,151],"limited":[42],"the":[44,47,52,66,88,93,98,108,130,138,143,155,170,175,179,190],"distribution":[45],"of":[46,61,68,92,116,145,178,192],"data":[48],"used":[49,119],"train":[51,74],"model.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"an":[59,114,126,164],"analysis":[60],"using":[62,78],"autoencoders":[63],"improve":[65,189],"generalisability":[67,144,191],"DL":[69,193],"solutions.":[72,196],"We":[73],"sparse":[76],"autoencoder":[77,94,171,185],"large":[80],"speech":[81,120],"corpus":[82,128,181],"extracted":[83],"from":[84],"social":[85],"media.":[86],"Later,":[87],"trained":[89,162],"encoder":[90,156],"part":[91],"reused":[96],"as":[97],"input":[99],"long":[102],"short-term":[103],"memory":[104],"(LSTM)":[105],"network,":[106],"and":[107,141,159],"encoder-LSTM":[109],"modal":[110],"re-trained":[112],"aggregation":[115],"five":[117],"commonly":[118],"emotion":[121],"corpora.":[122],"Our":[123,166],"evaluation":[124],"uses":[125],"unseen":[127,180],"training":[131],"&":[132],"validation":[133],"stages":[134],"simulate":[136],"'in":[137],"wild'":[139],"condition":[140],"analyse":[142],"our":[146],"solution.":[147],"A":[148],"comparison":[150],"carried":[152],"out":[153],"between":[154],"model":[158,161,173],"without":[163],"encoder.":[165],"results":[167],"show":[168],"improves":[174],"unweighted":[176],"accuracy":[177],"by":[182],"8%,":[183],"indicating":[184],"pre-training":[187],"can":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
