{"id":"https://openalex.org/W4406416457","doi":"https://doi.org/10.1109/ic3i61595.2024.10828860","title":"Emotion State Detection via Speech using Deep Learning","display_name":"Emotion State Detection via Speech using Deep Learning","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4406416457","doi":"https://doi.org/10.1109/ic3i61595.2024.10828860"},"language":"en","primary_location":{"id":"doi:10.1109/ic3i61595.2024.10828860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i61595.2024.10828860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Contemporary Computing and Informatics (IC3I)","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/A5009840867","display_name":"Rashmi Gupta","orcid":"https://orcid.org/0000-0003-0046-6700"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rashmi Gupta","raw_affiliation_strings":["Atal Bihari Vajpayee University,Department of Computer Science and Application,Bilaspur,Chhattisgarh,India"],"affiliations":[{"raw_affiliation_string":"Atal Bihari Vajpayee University,Department of Computer Science and Application,Bilaspur,Chhattisgarh,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027025211","display_name":"Jeetendra Kumar","orcid":"https://orcid.org/0000-0002-5705-6369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeetendra Kumar","raw_affiliation_strings":["Atal Bihari Vajpayee University,Department of Computer Science and Application,Bilaspur,Chhattisgarh,India"],"affiliations":[{"raw_affiliation_string":"Atal Bihari Vajpayee University,Department of Computer Science and Application,Bilaspur,Chhattisgarh,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026796612","display_name":"Suvarna Sharma","orcid":"https://orcid.org/0000-0003-4242-7646"},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suvarna Sharma","raw_affiliation_strings":["Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India"],"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering and Technology Chitkara University,Rajpura,Punjab,India","institution_ids":["https://openalex.org/I74319210"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009840867"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31651697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"491","last_page":"497"},"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":0.9914000034332275,"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/T13289","display_name":"Infant Health and Development","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287454605102539},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6137806177139282},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4951130449771881},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47522643208503723},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4686751961708069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44289225339889526},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42223241925239563},{"id":"https://openalex.org/keywords/emotion-detection","display_name":"Emotion detection","score":0.4137265086174011},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3474203646183014},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2834223508834839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287454605102539},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6137806177139282},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4951130449771881},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47522643208503723},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4686751961708069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44289225339889526},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42223241925239563},{"id":"https://openalex.org/C2988148770","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion detection","level":3,"score":0.4137265086174011},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3474203646183014},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2834223508834839},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic3i61595.2024.10828860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i61595.2024.10828860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Contemporary Computing and Informatics (IC3I)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2003837801","https://openalex.org/W2026984028","https://openalex.org/W2064641533","https://openalex.org/W2066312930","https://openalex.org/W2111926505","https://openalex.org/W2131406347","https://openalex.org/W2803193013","https://openalex.org/W2889445231","https://openalex.org/W2889717020","https://openalex.org/W2969889150","https://openalex.org/W3033283024","https://openalex.org/W3174977633","https://openalex.org/W4221046698","https://openalex.org/W4324382619","https://openalex.org/W4381166482","https://openalex.org/W4385814073","https://openalex.org/W4387712775","https://openalex.org/W4399042435"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W3126677997","https://openalex.org/W1610857240","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559837139"],"abstract_inverted_index":{"Oral":[0],"communication":[1],"is":[2,31],"the":[3,46,76,107],"most":[4],"efficient":[5],"and":[6,40,48,51,68,82,109,121],"common":[7],"way":[8],"to":[9,14,34],"interact":[10],"with":[11,112],"someone.":[12],"Due":[13],"this,":[15],"voice":[16],"signalling":[17],"has":[18],"attracted":[19],"researchers":[20],"for":[21],"its":[22],"potential":[23],"in":[24,105],"computer-human":[25],"communication.":[26],"Identifying":[27],"emotions":[28],"through":[29],"speech":[30],"complex":[32],"due":[33],"various":[35],"factors":[36],"like":[37],"feature":[38],"selection":[39],"vocal":[41],"diversity.":[42],"This":[43],"study":[44],"uses":[45],"RAVDESS":[47,108],"SAVEE":[49,110],"datasets":[50],"employs":[52],"techniques":[53],"including":[54],"Multilayer":[55],"Perceptron,":[56],"Random":[57],"Forest,":[58],"Support":[59],"Vector":[60],"Machine,":[61],"k-Nearest":[62],"Neighbours,":[63],"Logistic":[64],"Regression,":[65],"Gaussian-Neural":[66],"Network,":[67],"Convolutional":[69],"Neural":[70],"Network.":[71],"The":[72],"identified":[73],"features":[74],"encompass":[75],"MelFrequency":[77],"Cepstral":[78],"Coefficients":[79],"(MFCC),":[80],"Chroma,":[81],"Mel":[83],"spectrogram.":[84],"To":[85],"conduct":[86],"a":[87],"comparison":[88],"of":[89,115],"accuracy":[90,113],"rates,":[91],"we":[92],"employed":[93],"seven":[94],"classifiers":[95],"across":[96],"two":[97],"datasets.":[98],"Consequently,":[99],"CNN":[100],"model":[101],"demonstrated":[102],"superior":[103],"performance":[104],"both":[106],"databases,":[111],"rates":[114],"$\\mathbf{9":[116,122],"6.":[117],"7":[118],"5":[119],"\\%}$":[120,126],"2.":[123],"3":[124],"6":[125],"respectively,":[127],"surpassing":[128],"other":[129],"classifiers.":[130]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}