{"id":"https://openalex.org/W3209572141","doi":"https://doi.org/10.1109/tcds.2021.3123979","title":"Convolutional-Recurrent Neural Networks With Multiple Attention Mechanisms for Speech Emotion Recognition","display_name":"Convolutional-Recurrent Neural Networks With Multiple Attention Mechanisms for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-10-29","ids":{"openalex":"https://openalex.org/W3209572141","doi":"https://doi.org/10.1109/tcds.2021.3123979","mag":"3209572141"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2021.3123979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3123979","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","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/A5067420587","display_name":"Pengxu JIANG","orcid":"https://orcid.org/0000-0003-1738-1455"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengxu Jiang","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049684805","display_name":"Xinzhou Xu","orcid":"https://orcid.org/0000-0002-4017-5919"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhou Xu","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China","School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075748715","display_name":"Huawei Tao","orcid":"https://orcid.org/0000-0002-9194-0297"},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huawei Tao","raw_affiliation_strings":["College of Information Science and Technology, Henan University of Technology, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Henan University of Technology, Zhengzhou, China","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101872701","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0002-7145-4718"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112110256","display_name":"Cairong Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cairong Zou","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5067420587"],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":4.5883,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.95022637,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"14","issue":"4","first_page":"1564","last_page":"1573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.874731183052063},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6546981334686279},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6513992547988892},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5737236738204956},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.567371129989624},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5664319396018982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5290846824645996},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.45147034525871277},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4394640028476715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38355451822280884},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31391414999961853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.874731183052063},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6546981334686279},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6513992547988892},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5737236738204956},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.567371129989624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5664319396018982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5290846824645996},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.45147034525871277},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4394640028476715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38355451822280884},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31391414999961853},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2021.3123979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3123979","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4023624630","display_name":null,"funder_award_id":"BK20180746","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5250479028","display_name":null,"funder_award_id":"61801241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6249807887","display_name":null,"funder_award_id":"2020YFC2004003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W211912913","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1902237438","https://openalex.org/W1972137667","https://openalex.org/W2000436309","https://openalex.org/W2005708641","https://openalex.org/W2018549299","https://openalex.org/W2064675550","https://openalex.org/W2087618018","https://openalex.org/W2099767163","https://openalex.org/W2100495367","https://openalex.org/W2111926505","https://openalex.org/W2112796928","https://openalex.org/W2146334809","https://openalex.org/W2158061940","https://openalex.org/W2163605009","https://openalex.org/W2168692779","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2344225493","https://openalex.org/W2398881374","https://openalex.org/W2399733683","https://openalex.org/W2470673105","https://openalex.org/W2512885694","https://openalex.org/W2606705624","https://openalex.org/W2610961739","https://openalex.org/W2625297138","https://openalex.org/W2703895418","https://openalex.org/W2765860599","https://openalex.org/W2766272105","https://openalex.org/W2792059711","https://openalex.org/W2800146313","https://openalex.org/W2803098682","https://openalex.org/W2806649730","https://openalex.org/W2884001105","https://openalex.org/W2884585870","https://openalex.org/W2885005742","https://openalex.org/W2888731576","https://openalex.org/W2888792135","https://openalex.org/W2888910451","https://openalex.org/W2889191349","https://openalex.org/W2889191742","https://openalex.org/W2889507358","https://openalex.org/W2889544113","https://openalex.org/W2936451900","https://openalex.org/W2939129695","https://openalex.org/W2955793676","https://openalex.org/W2955983821","https://openalex.org/W2956824775","https://openalex.org/W2959133507","https://openalex.org/W2959546144","https://openalex.org/W2963091558","https://openalex.org/W2963481014","https://openalex.org/W2997026866","https://openalex.org/W2997399314","https://openalex.org/W3015267357","https://openalex.org/W3022569189","https://openalex.org/W3047923429","https://openalex.org/W3162475537","https://openalex.org/W4297779827","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6739901393","https://openalex.org/W6746034047","https://openalex.org/W6753412334","https://openalex.org/W6771497439"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3103566983"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"aims":[4],"to":[5,28,38,44,93],"endow":[6],"machines":[7],"with":[8,61,167],"the":[9,19,72,106,115,127,131,139,142,153,156,161],"intelligence":[10],"in":[11,35,46,68,91,114],"perceiving":[12],"latent":[13],"affective":[14],"components":[15],"from":[16],"speech.":[17],"However,":[18],"existing":[20,172],"works":[21],"on":[22,118,147],"deep-learning-based":[23],"SER":[24,67,150],"make":[25],"it":[26],"difficult":[27],"jointly":[29],"consider":[30],"time\u2013frequency":[31,95],"and":[32,78,87,96,133,163,171],"sequential":[33,97],"information":[34,98],"speech":[36],"due":[37],"their":[39],"structures,":[40],"which":[41],"may":[42],"lead":[43],"deficiencies":[45],"exploring":[47],"reasonable":[48],"local":[49],"emotional":[50],"representations.":[51],"In":[52],"this":[53,69],"regard,":[54],"we":[55,101],"propose":[56],"a":[57,110,122,135],"convolutional-recurrent":[58,162],"neural":[59,75],"network":[60,76],"multiple":[62,111],"attention":[63,124],"mechanisms":[64],"(CRNN-MAs)":[65],"for":[66,105],"article,":[70],"including":[71],"paralleled":[73],"convolutional":[74],"(CNN)":[77],"long":[79],"short-term":[80],"memory":[81],"(LSTM)":[82],"modules,":[83,165],"using":[84,160],"extracted":[85],"Mel-spectrums":[86],"frame-level":[88,119],"features,":[89],"respectively,":[90],"order":[92],"acquire":[94],"simultaneously.":[99],"Furthermore,":[100],"set":[102],"three":[103,148],"strategies":[104],"proposed":[107,157],"CRNN-MA:":[108],"1)":[109],"self-attention":[112],"layer":[113,125,137],"CNN":[116],"module":[117],"weights;":[120],"2)":[121],"multidimensional":[123],"as":[126],"input":[128],"features":[129,140],"of":[130,141,155],"LSTM;":[132],"3)":[134],"fusion":[136],"summarizing":[138],"two":[143],"modules.":[144],"Experimental":[145],"results":[146],"conventional":[149],"corpora":[151],"demonstrate":[152],"effectiveness":[154],"approach":[158],"through":[159],"multiple-attention":[164],"compared":[166],"other":[168],"related":[169],"models":[170],"state-of-the-art":[173],"approaches.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}