{"id":"https://openalex.org/W4411098909","doi":"https://doi.org/10.1145/3723178.3723262","title":"Bangla Speech Emotion Recognition Based on Audio Features Using CNN and LSTM","display_name":"Bangla Speech Emotion Recognition Based on Audio Features Using CNN and LSTM","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4411098909","doi":"https://doi.org/10.1145/3723178.3723262"},"language":"en","primary_location":{"id":"doi:10.1145/3723178.3723262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723178.3723262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723178.3723262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Computing Advancements","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3723178.3723262","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118281817","display_name":"Plabon Talukder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148693","display_name":"Metropolitan University","ror":"https://ror.org/04hdrrs71","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210148693"]},{"id":"https://openalex.org/I902853133","display_name":"University of Rajshahi","ror":"https://ror.org/05nnyr510","country_code":"BD","type":"education","lineage":["https://openalex.org/I902853133"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Plabon Talukder","raw_affiliation_strings":["Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh and Computer Science & Engineering, Metropolitan University, Sylhet, Sylhet, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0004-3792-0801","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh and Computer Science & Engineering, Metropolitan University, Sylhet, Sylhet, Bangladesh","institution_ids":["https://openalex.org/I902853133","https://openalex.org/I4210148693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017018760","display_name":"Md. Faysal Ahamed","orcid":"https://orcid.org/0000-0002-7014-3205"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Faysal Ahamed","raw_affiliation_strings":["Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-7014-3205","affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100388007","display_name":"Md. Rabiul Islam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md. Rabiul Islam","raw_affiliation_strings":["Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-1989-4385","affiliations":[{"raw_affiliation_string":"Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi, Rajshahi, Bangladesh","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5118281817"],"corresponding_institution_ids":["https://openalex.org/I4210148693","https://openalex.org/I902853133"],"apc_list":null,"apc_paid":null,"fwci":0.3288,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61172666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9965999722480774,"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/T13289","display_name":"Infant Health and Development","score":0.9868999719619751,"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/bengali","display_name":"Bengali","score":0.8483724594116211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114473819732666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.771899402141571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49777987599372864},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4913617670536041},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4592222571372986}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.8483724594116211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114473819732666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.771899402141571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49777987599372864},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4913617670536041},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4592222571372986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3723178.3723262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723178.3723262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723178.3723262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Computing Advancements","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3723178.3723262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3723178.3723262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3723178.3723262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Computing Advancements","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411098909.pdf","grobid_xml":"https://content.openalex.org/works/W4411098909.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2538101627","https://openalex.org/W2598207902","https://openalex.org/W2747664154","https://openalex.org/W2889717020","https://openalex.org/W2893184416","https://openalex.org/W2951442257","https://openalex.org/W2970737019","https://openalex.org/W3002872170","https://openalex.org/W3109961563","https://openalex.org/W3158346300","https://openalex.org/W4205131079","https://openalex.org/W4220754084","https://openalex.org/W4380189686"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2028401451","https://openalex.org/W2769530083","https://openalex.org/W3161006337","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Research":[0],"on":[1,90],"Bangla":[2,27,112],"Speech":[3],"Emotion":[4],"Recognition":[5],"(SER)":[6],"has":[7],"been":[8],"notably":[9],"limited":[10],"due":[11],"to":[12,25,34,53,102],"data":[13],"scarcity.This":[14],"study":[15],"utilizes":[16],"advanced":[17],"machine":[18],"learning":[19],"techniques":[20],"with":[21,69],"the":[22,54,91,100],"SUBESCO":[23,92],"dataset":[24,33],"enhance":[26],"SER":[28,118],"capabilities.We":[29],"methodically":[30],"processed":[31],"this":[32],"extract":[35],"key":[36],"features":[37],"such":[38],"as":[39],"Mel-frequency":[40],"cepstral":[41],"coefficients":[42],"(MFCC),":[43],"zero":[44],"crossing":[45],"rate,":[46],"root":[47],"mean":[48],"square":[49],"energy,":[50],"etc.,":[51],"owing":[52],"MFCCs'":[55],"effectiveness":[56],"in":[57,111],"succinctly":[58],"capturing":[59],"speech":[60],"dynamics.A":[61],"hybrid":[62],"model":[63],"combining":[64],"Convolutional":[65],"Neural":[66],"Networks":[67],"(CNN)":[68],"Bidirectional":[70],"Long":[71],"Short-Term":[72],"Memory":[73],"(LSTM)":[74],"and":[75,85,97],"dense":[76],"layers":[77],"was":[78],"developed,":[79],"achieving":[80],"an":[81],"accuracy":[82],"of":[83,88,95],"88.42%":[84],"a":[86,108,123],"loss":[87],"0.3546":[89],"dataset.The":[93],"integration":[94],"CNN":[96],"LSTM":[98],"enhanced":[99],"ability":[101],"interpret":[103],"complex":[104],"emotional":[105],"expressions,":[106],"marking":[107],"significant":[109],"advancement":[110],"SER.These":[113],"findings":[114],"not":[115],"only":[116],"propel":[117],"forward":[119],"but":[120],"also":[121],"set":[122],"foundation":[124],"for":[125,129],"improved":[126],"human-technology":[127],"interactions":[128],"other":[130],"underrepresented":[131],"languages.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}