{"id":"https://openalex.org/W3092190487","doi":"https://doi.org/10.1109/tnnls.2020.3027600","title":"Improving Speech Emotion Recognition With Adversarial Data Augmentation Network","display_name":"Improving Speech Emotion Recognition With Adversarial Data Augmentation Network","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3092190487","doi":"https://doi.org/10.1109/tnnls.2020.3027600","mag":"3092190487","pmid":"https://pubmed.ncbi.nlm.nih.gov/33035171"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3027600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3027600","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95326/1/T-NNLS-emotion.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008845262","display_name":"Yi Lu","orcid":"https://orcid.org/0000-0002-4803-9305"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lu Yi","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-4803-9305","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8854-3760","affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1882,"has_fulltext":true,"cited_by_count":115,"citation_normalized_percentile":{"value":0.96543108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"33","issue":"1","first_page":"172","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.8137588500976562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7590776681900024},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7503352165222168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6423292756080627},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5695279240608215},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5416922569274902},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5117576122283936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5080549716949463},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46396932005882263},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4093448519706726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38961368799209595}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8137588500976562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590776681900024},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7503352165222168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6423292756080627},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5695279240608215},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5416922569274902},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5117576122283936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5080549716949463},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46396932005882263},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4093448519706726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38961368799209595}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004644","descriptor_name":"Emotions","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019277","descriptor_name":"Entropy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2020.3027600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3027600","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:33035171","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33035171","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/95326","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/95326","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95326/1/T-NNLS-emotion.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/95326","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/95326","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/95326/1/T-NNLS-emotion.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"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":"Journal/Magazine Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8347340539","display_name":null,"funder_award_id":"PolyU152518/16E","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"},{"id":"https://openalex.org/G845204924","display_name":null,"funder_award_id":"PolyU152137/17E","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3092190487.pdf","grobid_xml":"https://content.openalex.org/works/W3092190487.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W105569935","https://openalex.org/W147964346","https://openalex.org/W175750906","https://openalex.org/W1019830208","https://openalex.org/W1493163583","https://openalex.org/W1501669607","https://openalex.org/W1975900269","https://openalex.org/W2050752817","https://openalex.org/W2055911634","https://openalex.org/W2058819080","https://openalex.org/W2060300932","https://openalex.org/W2090777335","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2125865219","https://openalex.org/W2146334809","https://openalex.org/W2160815625","https://openalex.org/W2165698076","https://openalex.org/W2168045655","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2296199791","https://openalex.org/W2306941105","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2512449761","https://openalex.org/W2602034649","https://openalex.org/W2765860599","https://openalex.org/W2770173563","https://openalex.org/W2770645414","https://openalex.org/W2786808285","https://openalex.org/W2800253600","https://openalex.org/W2802061317","https://openalex.org/W2885005742","https://openalex.org/W2888786729","https://openalex.org/W2889374687","https://openalex.org/W2889544113","https://openalex.org/W2891138528","https://openalex.org/W2897132394","https://openalex.org/W2943547402","https://openalex.org/W2945047231","https://openalex.org/W2950190315","https://openalex.org/W2951751045","https://openalex.org/W2962686539","https://openalex.org/W2962993399","https://openalex.org/W2963130397","https://openalex.org/W2964182121","https://openalex.org/W2964201867","https://openalex.org/W2990257819","https://openalex.org/W3011640397","https://openalex.org/W3103870504","https://openalex.org/W4239447739","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6678815747","https://openalex.org/W6681017033","https://openalex.org/W6732249622","https://openalex.org/W6735249503","https://openalex.org/W6735913928","https://openalex.org/W6741832134","https://openalex.org/W6746638498","https://openalex.org/W6780248173"],"related_works":["https://openalex.org/W4289763776","https://openalex.org/W2810330923","https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4220682630","https://openalex.org/W4389832810"],"abstract_inverted_index":{"When":[0],"training":[1,81,84],"data":[2,28,32,82,125,161],"are":[3,56,167,177],"scarce,":[4],"it":[5],"is":[6,99],"challenging":[7],"to":[8,59,78,104,114,142],"train":[9],"a":[10,26,46,144],"deep":[11],"neural":[12],"network":[13,34],"without":[14],"causing":[15],"the":[16,66,70,79,89,96,123,133,138,147,159,164,173],"overfitting":[17],"problem.":[18],"For":[19],"overcoming":[20],"this":[21,23],"challenge,":[22],"article":[24],"proposes":[25],"new":[27],"augmentation":[29,33],"network-namely":[30],"adversarial":[31,39,94],"(ADAN)-":[35],"based":[36],"on":[37],"generative":[38],"networks":[40,55,111,166],"(GANs).":[41],"The":[42,109],"ADAN":[43],"consists":[44],"of":[45,87],"GAN,":[47],"an":[48,51,102],"autoencoder,":[49],"and":[50,69,120,137],"auxiliary":[52],"classifier.":[53],"These":[54],"trained":[57],"adversarially":[58],"synthesize":[60],"class-dependent":[61],"feature":[62,72],"vectors":[63,136,141],"in":[64,101,169],"both":[65],"latent":[67,135,140],"space":[68],"original":[71],"space,":[73],"which":[74],"can":[75,151],"be":[76,152],"augmented":[77,160],"real":[80,139],"for":[83,93],"classifiers.":[85],"Instead":[86],"using":[88,118],"conventional":[90],"cross-entropy":[91],"loss":[92],"training,":[95],"Wasserstein":[97],"divergence":[98],"used":[100],"attempt":[103],"produce":[105],"high-quality":[106],"synthetic":[107,134],"samples.":[108],"proposed":[110,165],"were":[112],"applied":[113],"speech":[115,181],"emotion":[116,170,175,182],"recognition":[117,183],"EmoDB":[119],"IEMOCAP":[121],"as":[122],"evaluation":[124],"sets.":[126],"It":[127],"was":[128],"found":[129],"that":[130,158],"by":[131,163],"forcing":[132],"share":[143],"common":[145],"representation,":[146],"gradient":[148],"vanishing":[149],"problem":[150],"largely":[153],"alleviated.":[154],"Also,":[155],"results":[156],"show":[157],"generated":[162],"rich":[168],"information.":[171],"Thus,":[172],"resulting":[174],"classifiers":[176],"competitive":[178],"with":[179],"state-of-the-art":[180],"systems.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":31},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}