{"id":"https://openalex.org/W3002872170","doi":"https://doi.org/10.1109/access.2020.2967791","title":"Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends","display_name":"Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3002872170","doi":"https://doi.org/10.1109/access.2020.2967791","mag":"3002872170"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2967791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2967791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08963694.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08963694.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009370806","display_name":"Zhichao Peng","orcid":"https://orcid.org/0000-0003-1020-7796"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["CN","JP"],"is_corresponding":true,"raw_author_name":"Zhichao Peng","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559550","display_name":"Xingfeng Li","orcid":"https://orcid.org/0000-0002-8958-0341"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xingfeng Li","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089591444","display_name":"Zhi Zhu","orcid":"https://orcid.org/0000-0002-1525-9395"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zhi Zhu","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Unoki","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","Peng Cheng Laboratory, Shenzhen, China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009370806"],"corresponding_institution_ids":["https://openalex.org/I162868743","https://openalex.org/I177738480"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":9.6633,"has_fulltext":true,"cited_by_count":82,"citation_normalized_percentile":{"value":0.98399117,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":null,"first_page":"16560","last_page":"16572"},"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9879000186920166,"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":0.7372710704803467},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6156859993934631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.610687255859375},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5245707035064697},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4782366156578064},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4699155390262604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3615628778934479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372710704803467},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6156859993934631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.610687255859375},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5245707035064697},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4782366156578064},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4699155390262604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3615628778934479},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2020.2967791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2967791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08963694.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0f13d0eb0e6849aabbd453feb2e6de0f","is_oa":true,"landing_page_url":"https://doaj.org/article/0f13d0eb0e6849aabbd453feb2e6de0f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 16560-16572 (2020)","raw_type":"article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/16212","is_oa":true,"landing_page_url":"http://hdl.handle.net/10119/16212","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"doi:10.1109/access.2020.2967791","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2967791","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/08963694.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7085648200","display_name":"A study on production mechanism and modeling of emotional speech","funder_award_id":"16K00297","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3002872170.pdf","grobid_xml":"https://content.openalex.org/works/W3002872170.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1967789223","https://openalex.org/W1969851134","https://openalex.org/W1987292616","https://openalex.org/W2008806652","https://openalex.org/W2023020598","https://openalex.org/W2050758723","https://openalex.org/W2054883573","https://openalex.org/W2062663442","https://openalex.org/W2064641533","https://openalex.org/W2071554943","https://openalex.org/W2074788634","https://openalex.org/W2076502758","https://openalex.org/W2085662862","https://openalex.org/W2087618018","https://openalex.org/W2103253424","https://openalex.org/W2133990480","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2153635508","https://openalex.org/W2157184970","https://openalex.org/W2166756233","https://openalex.org/W2342475039","https://openalex.org/W2343758848","https://openalex.org/W2408520939","https://openalex.org/W2512449761","https://openalex.org/W2512885694","https://openalex.org/W2514017951","https://openalex.org/W2578895956","https://openalex.org/W2595328592","https://openalex.org/W2599621350","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2766272105","https://openalex.org/W2800311957","https://openalex.org/W2802402824","https://openalex.org/W2885005742","https://openalex.org/W2889507358","https://openalex.org/W2898004252","https://openalex.org/W2899172842","https://openalex.org/W2936451900","https://openalex.org/W2962736520","https://openalex.org/W2963467407","https://openalex.org/W2964113820","https://openalex.org/W2972498864","https://openalex.org/W2972602947","https://openalex.org/W2973037561","https://openalex.org/W4239339398","https://openalex.org/W6630073874","https://openalex.org/W6681409903","https://openalex.org/W6714031499","https://openalex.org/W6725773563"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W4327728159","https://openalex.org/W1990856605","https://openalex.org/W2053783616","https://openalex.org/W2545348020","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotion":[0],"information":[1],"from":[2,105,153],"speech":[3,43,152],"can":[4,19,143],"effectively":[5,145],"help":[6],"robots":[7],"understand":[8],"speaker's":[9],"intentions":[10],"in":[11,175],"natural":[12],"human-robot":[13],"interaction.":[14],"The":[15,157],"human":[16,173],"auditory":[17,49,95,106],"system":[18],"easily":[20],"track":[21],"temporal":[22,102,154],"dynamics":[23],"of":[24,33,85,151,165],"emotion":[25,40,44,68,72,86,128],"by":[26],"perceiving":[27],"the":[28,38,48,71,82,94,133,140,149,162,166,177],"intensity":[29],"and":[30,35,51,96,108,120,135],"fundamental":[31],"frequency":[32],"speech,":[34],"focus":[36],"on":[37,132],"salient":[39,83],"regions.":[41],"Therefore,":[42],"recognition":[45],"combined":[46],"with":[47,172],"mechanism":[50,53],"attention":[52,78,97,163,167],"may":[54],"be":[55,144],"an":[56],"effective":[57],"way.":[58],"Some":[59,74],"previous":[60],"studies":[61,76],"used":[62,77,146],"auditory-based":[63],"static":[64],"features":[65],"to":[66,80,147],"identify":[67],"while":[69,87],"ignoring":[70,88],"dynamics.":[73],"other":[75],"models":[79],"capture":[81],"regions":[84],"cognitive":[89],"continuity.":[90],"To":[91],"fully":[92],"utilize":[93],"mechanism,":[98],"we":[99],"first":[100],"investigate":[101],"modulation":[103,155],"cues":[104],"front-ends":[107],"then":[109],"propose":[110],"a":[111],"joint":[112],"deep":[113],"learning":[114],"model":[115,168],"that":[116,139,161],"combines":[117],"3D":[118],"convolutions":[119],"attention-based":[121],"sliding":[122],"recurrent":[123],"neural":[124],"networks":[125],"(ASRNNs)":[126],"for":[127],"recognition.":[129],"Our":[130],"experiments":[131],"IEMOCAP":[134],"MSP-IMPROV":[136],"datasets":[137],"indicate":[138],"proposed":[141],"method":[142],"recognize":[148],"emotions":[150],"cues.":[156],"subjective":[158],"evaluation":[159],"shows":[160],"patterns":[164],"are":[169],"basically":[170],"consistent":[171],"behaviors":[174],"recognizing":[176],"emotions.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}