{"id":"https://openalex.org/W4388937790","doi":"https://doi.org/10.1109/icccnt56998.2023.10306801","title":"Ensemble Integration of Deep Learning Models for Gender-Based Speech Emotion Recognition","display_name":"Ensemble Integration of Deep Learning Models for Gender-Based Speech Emotion Recognition","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4388937790","doi":"https://doi.org/10.1109/icccnt56998.2023.10306801"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt56998.2023.10306801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10306801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5061550392","display_name":"Gunti Swathi","orcid":"https://orcid.org/0009-0006-8171-2182"},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Gunti Swathi","raw_affiliation_strings":["Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103"],"affiliations":[{"raw_affiliation_string":"Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111727218","display_name":"R Prasanna Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R Prasanna Kumar","raw_affiliation_strings":["Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103"],"affiliations":[{"raw_affiliation_string":"Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002643721","display_name":"Bharathi Mohan G","orcid":null},"institutions":[{"id":"https://openalex.org/I81556334","display_name":"Amrita Vishwa Vidyapeetham","ror":"https://ror.org/03am10p12","country_code":"IN","type":"education","lineage":["https://openalex.org/I81556334"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bharathi Mohan G","raw_affiliation_strings":["Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103"],"affiliations":[{"raw_affiliation_string":"Amrita Vishwa Vidyapeetham,Amrita School of Computing,Department of Computer Science and Engineering,Chennai,India,601103","institution_ids":["https://openalex.org/I81556334"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065579469","display_name":"R Elakkiya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164135","display_name":"Birla Institute of Technology and Science, Pilani - Dubai Campus","ror":"https://ror.org/05jnbme07","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210164135","https://openalex.org/I74796645"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Elakkiya R","raw_affiliation_strings":["Birla Institute of Technology and Science,Department of Computer Science and Engineering,Dubai,UAE,345055"],"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science,Department of Computer Science and Engineering,Dubai,UAE,345055","institution_ids":["https://openalex.org/I4210164135"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061550392"],"corresponding_institution_ids":["https://openalex.org/I81556334"],"apc_list":null,"apc_paid":null,"fwci":1.0166,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77060775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8023942708969116},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6853023171424866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.639998197555542},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6197801232337952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6148039698600769},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5742691159248352},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5633003115653992},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.46334370970726013},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.462965726852417},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4537407159805298},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.4493928849697113},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4233432412147522},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.415568083524704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3727531433105469},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35731562972068787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33993247151374817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023942708969116},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6853023171424866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.639998197555542},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6197801232337952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6148039698600769},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5742691159248352},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5633003115653992},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.46334370970726013},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.462965726852417},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4537407159805298},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.4493928849697113},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4233432412147522},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.415568083524704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3727531433105469},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35731562972068787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33993247151374817},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt56998.2023.10306801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt56998.2023.10306801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W2030931454","https://openalex.org/W2059372649","https://openalex.org/W2125236659","https://openalex.org/W2154024118","https://openalex.org/W2155158173","https://openalex.org/W2156387975","https://openalex.org/W2513457117","https://openalex.org/W2598207902","https://openalex.org/W2622826443","https://openalex.org/W2785627692","https://openalex.org/W2803193013","https://openalex.org/W3015240477","https://openalex.org/W3076928706","https://openalex.org/W3081192838","https://openalex.org/W3084762076","https://openalex.org/W3093739508","https://openalex.org/W3134221487","https://openalex.org/W4212863985","https://openalex.org/W4221075235","https://openalex.org/W4226207398","https://openalex.org/W4250504904","https://openalex.org/W4285609027","https://openalex.org/W4289516314","https://openalex.org/W4318570632","https://openalex.org/W4323025035","https://openalex.org/W4362544719","https://openalex.org/W4365802711","https://openalex.org/W6629510986","https://openalex.org/W6638667902","https://openalex.org/W6747874431"],"related_works":["https://openalex.org/W1038900426","https://openalex.org/W2794896638","https://openalex.org/W1549141376","https://openalex.org/W2891633941","https://openalex.org/W3126677997","https://openalex.org/W4390905871","https://openalex.org/W2169648905","https://openalex.org/W3202800081","https://openalex.org/W3124390867","https://openalex.org/W3101614107"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,128],"recognition":[2],"(SER)":[3],"holds":[4],"significant":[5],"importance":[6],"in":[7,146],"numerous":[8],"applications,":[9],"as":[10,74],"it":[11],"heavily":[12],"relies":[13],"on":[14,65,116,138],"the":[15,51,158,161,169,179,183],"precise":[16],"extraction":[17],"of":[18,150,160,165,178,186],"acoustic":[19,52],"information":[20],"from":[21],"speech":[22,127],"signals.":[23],"However,":[24],"recognizing":[25],"emotions":[26],"within":[27],"a":[28,66,117],"complete":[29],"utterance":[30],"often":[31],"poses":[32],"challenges":[33],"due":[34],"to":[35,49,71,126],"inherent":[36],"ambiguity":[37],"and":[38,56,78,100,106,123,136,142],"varying":[39],"probabilities":[40],"assosiated":[41],"with":[42],"different":[43],"emotions.":[44],"Previous":[45],"approaches":[46],"have":[47],"failed":[48],"account":[50],"variances":[53],"between":[54],"male":[55],"female":[57],"speakers":[58],"by":[59,181],"employing":[60],"combined":[61],"dataset.":[62],"Furthermore,":[63],"relying":[64],"single":[67],"model":[68,90,133,163,173],"can":[69],"lead":[70],"limitations":[72],"such":[73],"reduced":[75],"robustness,":[76],"overfitting,":[77],"limited":[79],"generalization.":[80],"To":[81],"mitigate":[82],"these":[83],"issues,":[84],"this":[85],"paper":[86],"proposes":[87],"an":[88],"ensemble":[89,132],"that":[91,120,157],"combines":[92],"Convolutional":[93],"Neural":[94],"Network":[95],"(CNN),":[96],"Residual":[97],"CNN":[98],"(RCNN)":[99],"Long":[101],"Short-Term":[102],"Memory":[103],"(LSTM)":[104],"architectures":[105],"utilizes":[107],"features,":[108],"extracted":[109],"using":[110],"Mel":[111],"Frequency":[112],"Cepstral":[113],"Coefficients":[114],"(MFCC)":[115],"gender-differentiated":[118],"dataset":[119],"provides":[121],"comprehensive":[122],"robust":[124],"approach":[125],"recognition.":[129],"This":[130],"proposed":[131],"is":[134],"trained":[135],"evaluated":[137],"RAVDESS,":[139],"CREMA-D,":[140],"SAVEE":[141],"TESS":[143],"datasets,":[144],"resulting":[145],"weighted":[147],"mean":[148],"accuracy":[149],"95.54%.":[151],"The":[152,171],"obtained":[153],"results":[154],"clearly":[155],"indicate":[156],"utilization":[159],"Ensemble":[162,172],"instead":[164],"individual":[166],"models":[167],"improved":[168],"accuracy.":[170],"effectively":[174],"encompasses":[175],"diverse":[176],"aspects":[177],"data":[180],"leveraging":[182],"unique":[184],"strengths":[185],"each":[187],"model.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}