{"id":"https://openalex.org/W4381735375","doi":"https://doi.org/10.3233/aise230012","title":"Speech Emotion Recognition Using Deep Convolutional Neural Networks Improved by the Fast Continuous Wavelet Transform","display_name":"Speech Emotion Recognition Using Deep Convolutional Neural Networks Improved by the Fast Continuous Wavelet Transform","publication_year":2023,"publication_date":"2023-06-22","ids":{"openalex":"https://openalex.org/W4381735375","doi":"https://doi.org/10.3233/aise230012"},"language":"en","primary_location":{"id":"doi:10.3233/aise230012","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise230012","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE230012","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE230012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092242190","display_name":"Bj\u00f6rn E. Van Zwol","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Bj\u00f6rn E. Van Zwol","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092242191","display_name":"Mathijs A. Langezaal","orcid":"https://orcid.org/0000-0001-9978-9598"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]},{"id":"https://openalex.org/I4210103698","display_name":"Centre de recherche en Epid\u00e9miologie et Sant\u00e9 des Populations","ror":"https://ror.org/01ed4t417","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4210097159","https://openalex.org/I4210097159","https://openalex.org/I4210103698","https://openalex.org/I4210164847","https://openalex.org/I4405259118"]},{"id":"https://openalex.org/I4390039343","display_name":"Cohortes \u00e9pid\u00e9miologiques en population","ror":"https://ror.org/00ex3jm11","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I195731000","https://openalex.org/I204730241","https://openalex.org/I277688954","https://openalex.org/I277688954","https://openalex.org/I4390039343"]}],"countries":["FR","NL"],"is_corresponding":false,"raw_author_name":"Mathijs A. Langezaal","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","Population-Based Epidemiological Cohorts Unit UMS11, INSERM, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]},{"raw_affiliation_string":"Population-Based Epidemiological Cohorts Unit UMS11, INSERM, Paris, France","institution_ids":["https://openalex.org/I4210103698","https://openalex.org/I4390039343","https://openalex.org/I154526488"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059878919","display_name":"Lukas P.A. Arts","orcid":"https://orcid.org/0000-0001-8398-0259"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lukas P.A. Arts","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027041248","display_name":"Albert Gatt","orcid":"https://orcid.org/0000-0001-6388-8244"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Albert Gatt","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088241273","display_name":"Egon L. van den Broek","orcid":"https://orcid.org/0000-0002-2017-0141"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Egon L. Van Den Broek","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092242190"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":1.8523,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84239401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9911999702453613,"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/T11309","display_name":"Music and Audio Processing","score":0.984499990940094,"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":0.7278999090194702},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6978566646575928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6394399404525757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5799866318702698},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5741238594055176},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5368443131446838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5331593751907349},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4813712239265442},{"id":"https://openalex.org/keywords/continuous-wavelet-transform","display_name":"Continuous wavelet transform","score":0.459576815366745},{"id":"https://openalex.org/keywords/stationary-wavelet-transform","display_name":"Stationary wavelet transform","score":0.4187786281108856},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.3438018262386322},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.29799675941467285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7278999090194702},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6978566646575928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6394399404525757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799866318702698},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5741238594055176},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5368443131446838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5331593751907349},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4813712239265442},{"id":"https://openalex.org/C95722684","wikidata":"https://www.wikidata.org/wiki/Q2622756","display_name":"Continuous wavelet transform","level":5,"score":0.459576815366745},{"id":"https://openalex.org/C73339587","wikidata":"https://www.wikidata.org/wiki/Q1375942","display_name":"Stationary wavelet transform","level":5,"score":0.4187786281108856},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.3438018262386322},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.29799675941467285}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/aise230012","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise230012","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE230012","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},{"id":"pmh:oai:dspace.library.uu.nl:1874/430376","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/430376","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Part of book"}],"best_oa_location":{"id":"doi:10.3233/aise230012","is_oa":true,"landing_page_url":"https://doi.org/10.3233/aise230012","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/AISE230012","source":{"id":"https://openalex.org/S4210168452","display_name":"Ambient intelligence and smart environments","issn_l":"1875-4163","issn":["1875-4163","1875-4171"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ambient Intelligence and Smart Environments","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4482066628","display_name":null,"funder_award_id":"PNR EST-2018/1/106","funder_id":"https://openalex.org/F4320324529","funder_display_name":"Agence Nationale de S\u00e9curit\u00e9 Sanitaire de l\u2019Alimentation, de l\u2019Environnement et du Travail"},{"id":"https://openalex.org/G6943243190","display_name":"from Intrinsic Motivations to Transitional Wearable INtelligent companions for autism spectrum disorder","funder_award_id":"952095","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321010","display_name":"Universiteit Utrecht","ror":"https://ror.org/04pp8hn57"},{"id":"https://openalex.org/F4320324529","display_name":"Agence Nationale de S\u00e9curit\u00e9 Sanitaire de l\u2019Alimentation, de l\u2019Environnement et du Travail","ror":"https://ror.org/0471kz689"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4381735375.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W228380312","https://openalex.org/W1595810167","https://openalex.org/W1968531668","https://openalex.org/W2096653978","https://openalex.org/W2117539524","https://openalex.org/W2120351640","https://openalex.org/W2123130028","https://openalex.org/W2127314075","https://openalex.org/W2132909009","https://openalex.org/W2168692779","https://openalex.org/W2188563164","https://openalex.org/W2318109418","https://openalex.org/W2618530766","https://openalex.org/W2766272105","https://openalex.org/W2784665486","https://openalex.org/W2954996726","https://openalex.org/W2969889150","https://openalex.org/W2997123107","https://openalex.org/W3139270985","https://openalex.org/W3161428216","https://openalex.org/W3198872525","https://openalex.org/W4210713738","https://openalex.org/W4221094122","https://openalex.org/W4280542824","https://openalex.org/W4289684174","https://openalex.org/W6659539031"],"related_works":["https://openalex.org/W2046633342","https://openalex.org/W2085792030","https://openalex.org/W2351059076","https://openalex.org/W1588899229","https://openalex.org/W1967182499","https://openalex.org/W4321517526","https://openalex.org/W1976022598","https://openalex.org/W2391053410","https://openalex.org/W2968739105","https://openalex.org/W2111896212"],"abstract_inverted_index":{"The":[0],"fast":[1],"Continuous":[2],"Wavelet":[3],"Transform":[4],"(fCWT)":[5],"is":[6,69,93],"used":[7],"to":[8,40],"improve":[9],"Deep":[10],"Convolutional":[11],"Neural":[12],"Networks":[13],"(DCNN)\u2019s":[14],"Speech":[15],"Emotion":[16],"Recognition":[17],"(SER).":[18],"While":[19],"being":[20],"computationally":[21],"efficient,":[22],"the":[23,97,100],"fCWT\u2019s":[24,84],"time-frequency":[25],"analysis":[26],"overcomes":[27],"traditional":[28],"methods\u2019":[29],"resolution":[30],"limitations":[31],"(e.g.,":[32],"Short-Term":[33],"Fourier":[34],"Transform).":[35],"fCWT-induced":[36],"DCNNs":[37],"are":[38,82],"compared":[39],"state-of-the-art":[41],"DCNN":[42],"SER":[43,88],"systems.":[44],"Comparing":[45],"different":[46],"wavelet":[47],"parameters,":[48],"we":[49],"also":[50],"provide":[51],"an":[52],"empirical":[53],"strategy":[54,68],"for":[55,73,86],"balancing":[56],"temporal":[57],"and":[58],"spectral":[59],"features":[60],"in":[61,90,99],"speech":[62],"signals.":[63],"We":[64],"suggest":[65],"that":[66],"this":[67],"of":[70,80],"generic":[71],"interest":[72],"non-stationary":[74],"signal":[75],"processing":[76],"where":[77],"large":[78],"amounts":[79],"data":[81,109],"available.":[83],"potential":[85],"improving":[87],"accuracy":[89],"real-time":[91],"applications":[92],"confirmed.":[94],"In":[95],"parallel,":[96],"variance":[98],"cross-validation":[101],"folds":[102],"confirmed":[103],"deep":[104],"learning\u2019s":[105],"vulnerability":[106],"on":[107],"non-big":[108],"sets.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-22T09:01:20.584952","created_date":"2025-10-10T00:00:00"}