{"id":"https://openalex.org/W2964113820","doi":"https://doi.org/10.1109/acii.2017.8273628","title":"Learning spectro-temporal features with 3D CNNs for speech emotion recognition","display_name":"Learning spectro-temporal features with 3D CNNs for speech emotion recognition","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2964113820","doi":"https://doi.org/10.1109/acii.2017.8273628","mag":"2964113820"},"language":"en","primary_location":{"id":"doi:10.1109/acii.2017.8273628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2017.8273628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ris.utwente.nl/ws/files/358372893/Learning_spectro-temporal_features_with_3D_CNNs_for_speech_emotion_recognition.pdf","any_repository_has_fulltext":true},"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/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":"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":"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":3.7568,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.93335586,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987999796867371,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7469796538352966},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7279797792434692},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.697381317615509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6317948698997498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6257476806640625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6095960736274719},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6084508895874023},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5254302024841309},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4639434814453125},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4218592941761017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469796538352966},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7279797792434692},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.697381317615509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6317948698997498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6257476806640625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6095960736274719},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6084508895874023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5254302024841309},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4639434814453125},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4218592941761017},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/acii.2017.8273628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2017.8273628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:publications/45b76265-d38f-4d08-9636-fd6d25cd63cf","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/45b76265-d38f-4d08-9636-fd6d25cd63cf","pdf_url":"https://ris.utwente.nl/ws/files/358372893/Learning_spectro-temporal_features_with_3D_CNNs_for_speech_emotion_recognition.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Kim, J, Truong, K P, Englebienne, G & Evers, V 2018, Learning spectro-temporal features with 3D CNNs for speech emotion recognition. in 2017 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017. IEEE, pp. 383-388, 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017, San Antonio, Texas, United States, 23/10/17. https://doi.org/10.1109/ACII.2017.8273628","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:publications/45b76265-d38f-4d08-9636-fd6d25cd63cf","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/45b76265-d38f-4d08-9636-fd6d25cd63cf","pdf_url":"https://ris.utwente.nl/ws/files/358372893/Learning_spectro-temporal_features_with_3D_CNNs_for_speech_emotion_recognition.pdf","source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Kim, J, Truong, K P, Englebienne, G & Evers, V 2018, Learning spectro-temporal features with 3D CNNs for speech emotion recognition. in 2017 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017. IEEE, pp. 383-388, 7th International Conference on Affective Computing and Intelligent Interaction, ACII 2017, San Antonio, Texas, United States, 23/10/17. https://doi.org/10.1109/ACII.2017.8273628","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964113820.pdf","grobid_xml":"https://content.openalex.org/works/W2964113820.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W175750906","https://openalex.org/W1261896931","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1538131130","https://openalex.org/W1600744878","https://openalex.org/W1983364832","https://openalex.org/W2016043834","https://openalex.org/W2045528981","https://openalex.org/W2087618018","https://openalex.org/W2093174546","https://openalex.org/W2095705004","https://openalex.org/W2135776491","https://openalex.org/W2146334809","https://openalex.org/W2163922914","https://openalex.org/W2168692779","https://openalex.org/W2181741066","https://openalex.org/W2187089797","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2512449761","https://openalex.org/W2541674938","https://openalex.org/W2765998482","https://openalex.org/W2963410064","https://openalex.org/W2964121744","https://openalex.org/W2964128364","https://openalex.org/W4292865245","https://openalex.org/W6604065217","https://openalex.org/W6607193717","https://openalex.org/W6632100814","https://openalex.org/W6674330103","https://openalex.org/W6714031499","https://openalex.org/W6729059855","https://openalex.org/W6927634225"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,117],"propose":[4],"to":[5,15,29,113],"use":[6],"deep":[7,88],"3-dimensional":[8],"convolutional":[9],"networks":[10],"(3D":[11],"CNNs)":[12],"in":[13,64],"order":[14],"address":[16],"the":[17,98,119],"challenge":[18],"of":[19,32,54,78,91,138],"modelling":[20],"spectro-temporal":[21,109],"dynamics":[22],"for":[23,97,108],"speech":[24],"emotion":[25],"recognition":[26],"(SER).":[27],"Compared":[28],"a":[30,51,65,73,92],"hybrid":[31],"Convolutional":[33],"Neural":[34],"Network":[35],"and":[36,46,60,75,86,100,133],"Long-Short-Term-Memory":[37],"(CNN-LSTM),":[38],"our":[39,58,102,124],"proposed":[40,59,125],"3D":[41,103],"CNNs":[42,104],"simultaneously":[43],"extract":[44],"short-term":[45],"long-term":[47],"spectral":[48,89],"features":[49],"with":[50,123],"moderate":[52],"number":[53],"parameters.":[55],"We":[56,80],"evaluated":[57],"other":[61,114],"state-of-the-art":[62],"methods":[63],"speaker-independent":[66],"manner":[67],"using":[68,127],"aggregated":[69],"corpora":[70],"that":[71,82],"give":[72],"large":[74],"diverse":[76],"set":[77],"speakers.":[79],"found":[81],"1)":[83],"shallow":[84],"temporal":[85],"moderately":[87],"kernels":[90],"homogeneous":[93],"architecture":[94],"are":[95,105],"optimal":[96],"task;":[99],"2)":[101],"more":[106],"effective":[107],"feature":[110,120],"learning":[111],"compared":[112],"methods.":[115],"Finally,":[116],"visualised":[118],"space":[121],"obtained":[122],"method":[126],"t-distributed":[128],"stochastic":[129],"neighbour":[130],"embedding":[131],"(T-SNE)":[132],"could":[134],"observe":[135],"distinct":[136],"clusters":[137],"emotions.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-16T09:24:06.705377","created_date":"2025-10-10T00:00:00"}