{"id":"https://openalex.org/W3144479330","doi":"https://doi.org/10.1109/slt48900.2021.9383513","title":"Improving Convolutional Recurrent Neural Networks for Speech Emotion Recognition","display_name":"Improving Convolutional Recurrent Neural Networks for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3144479330","doi":"https://doi.org/10.1109/slt48900.2021.9383513","mag":"3144479330"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-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/A5019858282","display_name":"Patrick Meyer","orcid":"https://orcid.org/0000-0001-6479-213X"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Meyer","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070273121","display_name":"Ziyi Xu","orcid":"https://orcid.org/0000-0003-3046-1425"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziyi Xu","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019858282"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":2.4863,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88321099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"365","last_page":"372"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9993000030517578,"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":0.7992956638336182},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6747628450393677},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6039332151412964},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6004638671875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5331045389175415},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5007410049438477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4816685914993286},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4694848656654358},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4681912660598755},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46451395750045776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.462878942489624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44654443860054016},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43848344683647156},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43561851978302},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.422762930393219},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3153483271598816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992956638336182},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6747628450393677},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6039332151412964},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6004638671875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5331045389175415},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5007410049438477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4816685914993286},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4694848656654358},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4681912660598755},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46451395750045776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.462878942489624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44654443860054016},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43848344683647156},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43561851978302},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.422762930393219},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3153483271598816},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W1501669607","https://openalex.org/W1524333225","https://openalex.org/W1534131679","https://openalex.org/W1600744878","https://openalex.org/W1923034539","https://openalex.org/W2032254851","https://openalex.org/W2074788634","https://openalex.org/W2080576537","https://openalex.org/W2085662862","https://openalex.org/W2087618018","https://openalex.org/W2099767163","https://openalex.org/W2101234009","https://openalex.org/W2118911453","https://openalex.org/W2137639365","https://openalex.org/W2146334809","https://openalex.org/W2158061940","https://openalex.org/W2181741066","https://openalex.org/W2343758848","https://openalex.org/W2399125226","https://openalex.org/W2399733683","https://openalex.org/W2402144811","https://openalex.org/W2578895956","https://openalex.org/W2583743457","https://openalex.org/W2625426967","https://openalex.org/W2630837129","https://openalex.org/W2648194195","https://openalex.org/W2750666523","https://openalex.org/W2780113219","https://openalex.org/W2885005742","https://openalex.org/W2888786729","https://openalex.org/W2889084816","https://openalex.org/W2936774411","https://openalex.org/W2937154351","https://openalex.org/W2937584914","https://openalex.org/W2940259008","https://openalex.org/W2953384591","https://openalex.org/W2963087613","https://openalex.org/W2972498864","https://openalex.org/W2972688505","https://openalex.org/W3015267357","https://openalex.org/W6631362777","https://openalex.org/W6675354045","https://openalex.org/W6712977385","https://openalex.org/W6713134421","https://openalex.org/W6733353833","https://openalex.org/W6739009451","https://openalex.org/W6739696289"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W4306886878"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2,12,26],"increased":[3],"the":[4,50,80,123],"interest":[5],"in":[6,59,75,128],"speech":[7],"emotion":[8],"recognition":[9,43],"(SER)":[10],"and":[11,17,36,69,105],"put":[13],"forth":[14],"diverse":[15],"structures":[16],"methods":[18],"to":[19,113],"improve":[20],"performance.":[21],"In":[22,111],"recent":[23],"years":[24],"it":[25],"turned":[27],"out":[28],"that":[29],"applying":[30],"SER":[31,39],"on":[32,133,145,154],"a":[33,46,54,62,90,95],"(log-mel)":[34],"spectrogram":[35],"thus,":[37],"interpreting":[38],"as":[40],"an":[41,101,107,129,148],"image":[42],"task":[44],"is":[45],"promising":[47],"method.":[48,110],"Following":[49],"trend":[51],"towards":[52],"using":[53],"convolutional":[55],"neural":[56],"network":[57],"(CNN)":[58],"combination":[60],"with":[61,147],"bidirectional":[63],"long":[64],"short-term":[65],"memory":[66],"(BLSTM)":[67],"layer,":[68],"some":[70],"subsequent":[71],"fully":[72],"connected":[73],"layers,":[74],"this":[76,83,141],"work,":[77],"we":[78,120,136],"advance":[79],"performance":[81],"of":[82,125,143,152],"topology":[84,144],"by":[85],"several":[86],"contributions:":[87],"We":[88],"integrate":[89],"multi-kernel":[91],"width":[92],"CNN,":[93],"propose":[94],"BLSTM":[96],"output":[97],"summarization":[98],"function,":[99],"apply":[100],"enhanced":[102],"feature":[103],"representation,":[104],"introduce":[106],"effective":[108],"training":[109],"order":[112],"foster":[114],"insight":[115],"into":[116],"our":[117,134],"proposed":[118],"methods,":[119],"separately":[121],"evaluate":[122],"impact":[124],"each":[126],"modification":[127],"ablation":[130],"study.":[131],"Based":[132],"modifications,":[135],"obtain":[137],"top":[138],"results":[139],"for":[140],"type":[142],"IEMOCAP":[146],"unweighted":[149],"average":[150],"recall":[151],"64.5%":[153],"average.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}