{"id":"https://openalex.org/W4413416079","doi":"https://doi.org/10.3390/jimaging11080273","title":"Bangla Speech Emotion Recognition Using Deep Learning-Based Ensemble Learning and Feature Fusion","display_name":"Bangla Speech Emotion Recognition Using Deep Learning-Based Ensemble Learning and Feature Fusion","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W4413416079","doi":"https://doi.org/10.3390/jimaging11080273","pmid":"https://pubmed.ncbi.nlm.nih.gov/40863483"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11080273","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080273","pdf_url":"https://www.mdpi.com/2313-433X/11/8/273/pdf?version=1755228380","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/11/8/273/pdf?version=1755228380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084804881","display_name":"Md. Shahid Ahammed Shakil","orcid":"https://orcid.org/0009-0004-9610-9867"},"institutions":[{"id":"https://openalex.org/I260446899","display_name":"Pabna University of Science and Technology","ror":"https://ror.org/01vxg3438","country_code":"BD","type":"education","lineage":["https://openalex.org/I260446899"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Shahid Ahammed Shakil","raw_affiliation_strings":["Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0004-9610-9867","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh","institution_ids":["https://openalex.org/I260446899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044844639","display_name":"Fahmid Al Farid","orcid":"https://orcid.org/0000-0003-2625-2348"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Fahmid Al Farid","raw_affiliation_strings":["Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-2625-2348","affiliations":[{"raw_affiliation_string":"Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012935126","display_name":"Nitun Kumar Podder","orcid":"https://orcid.org/0000-0001-5448-4643"},"institutions":[{"id":"https://openalex.org/I260446899","display_name":"Pabna University of Science and Technology","ror":"https://ror.org/01vxg3438","country_code":"BD","type":"education","lineage":["https://openalex.org/I260446899"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Nitun Kumar Podder","raw_affiliation_strings":["Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh","institution_ids":["https://openalex.org/I260446899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112894860","display_name":"S. M. Hasan Sazzad Iqbal","orcid":null},"institutions":[{"id":"https://openalex.org/I260446899","display_name":"Pabna University of Science and Technology","ror":"https://ror.org/01vxg3438","country_code":"BD","type":"education","lineage":["https://openalex.org/I260446899"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"S. M. Hasan Sazzad Iqbal","raw_affiliation_strings":["Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh","institution_ids":["https://openalex.org/I260446899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017981507","display_name":"Abu Saleh Musa Miah","orcid":"https://orcid.org/0000-0002-1238-0464"},"institutions":[{"id":"https://openalex.org/I183697816","display_name":"Bangladesh University of Engineering and Technology","ror":"https://ror.org/05a1qpv97","country_code":"BD","type":"education","lineage":["https://openalex.org/I183697816"]},{"id":"https://openalex.org/I4403386503","display_name":"Bangladesh Army University of Science and Technology","ror":"https://ror.org/00xqgpg43","country_code":null,"type":"education","lineage":["https://openalex.org/I4403386503"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Abu Saleh Musa Miah","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology (BAUST), Saidpur 5311, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-1238-0464","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology (BAUST), Saidpur 5311, Bangladesh","institution_ids":["https://openalex.org/I183697816","https://openalex.org/I4403386503"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072523228","display_name":"Md Abdur Rahim","orcid":"https://orcid.org/0000-0003-2300-1420"},"institutions":[{"id":"https://openalex.org/I260446899","display_name":"Pabna University of Science and Technology","ror":"https://ror.org/01vxg3438","country_code":"BD","type":"education","lineage":["https://openalex.org/I260446899"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Md Abdur Rahim","raw_affiliation_strings":["Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-2300-1420","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pabna University of Science and Technology, Pabna 6600, Bangladesh","institution_ids":["https://openalex.org/I260446899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027445807","display_name":"Hezerul Abdul Karim","orcid":"https://orcid.org/0000-0002-7613-4596"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Hezerul Abdul Karim","raw_affiliation_strings":["Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-7613-4596","affiliations":[{"raw_affiliation_string":"Centre for Image and Vision Computing (CIVC), COE for Artificial Intelligence, Faculty of Artificial Intelligence and Engineering (FAIE), Multimedia University, Cyberjaya 63100, Selangor, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5017981507","https://openalex.org/A5027445807","https://openalex.org/A5072523228"],"corresponding_institution_ids":["https://openalex.org/I173029219","https://openalex.org/I183697816","https://openalex.org/I260446899","https://openalex.org/I4403386503"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":3.4248,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92912907,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"11","issue":"8","first_page":"273","last_page":"273"},"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":0.9994999766349792,"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":0.998199999332428,"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":0.7570915818214417},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.7480508089065552},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7103043794631958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6515398025512695},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6089847087860107},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5877820253372192},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5856983065605164},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5472698211669922},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4668019115924835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4590739905834198},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4181067645549774},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3582177758216858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570915818214417},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.7480508089065552},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7103043794631958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6515398025512695},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6089847087860107},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5877820253372192},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5856983065605164},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5472698211669922},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4668019115924835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4590739905834198},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4181067645549774},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3582177758216858},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging11080273","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080273","pdf_url":"https://www.mdpi.com/2313-433X/11/8/273/pdf?version=1755228380","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:40863483","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40863483","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:4c0edcae4eea4eea926c6a7ec0ee6fa6","is_oa":true,"landing_page_url":"https://doaj.org/article/4c0edcae4eea4eea926c6a7ec0ee6fa6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 11, Iss 8, p 273 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11195279","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12387467","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging11080273","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11080273","pdf_url":"https://www.mdpi.com/2313-433X/11/8/273/pdf?version=1755228380","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G622218618","display_name":null,"funder_award_id":"PostDoc(MMUI/240029)","funder_id":"https://openalex.org/F4320313202","funder_display_name":"Multimedia University"},{"id":"https://openalex.org/G8591213879","display_name":null,"funder_award_id":"MMUI/240029","funder_id":"https://openalex.org/F4320313202","funder_display_name":"Multimedia University"}],"funders":[{"id":"https://openalex.org/F4320313202","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413416079.pdf","grobid_xml":"https://content.openalex.org/works/W4413416079.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1861213619","https://openalex.org/W2095705004","https://openalex.org/W2155776568","https://openalex.org/W2181741066","https://openalex.org/W2191779130","https://openalex.org/W2273396394","https://openalex.org/W2598207902","https://openalex.org/W2762084293","https://openalex.org/W2803193013","https://openalex.org/W2889717020","https://openalex.org/W2893184416","https://openalex.org/W2951442257","https://openalex.org/W2969889150","https://openalex.org/W2976594877","https://openalex.org/W2997700007","https://openalex.org/W3008039831","https://openalex.org/W3035965352","https://openalex.org/W3094144570","https://openalex.org/W3095237804","https://openalex.org/W3099878876","https://openalex.org/W3120709499","https://openalex.org/W3134450397","https://openalex.org/W3140854437","https://openalex.org/W3158346300","https://openalex.org/W3173501672","https://openalex.org/W3194672963","https://openalex.org/W3209710747","https://openalex.org/W4205131079","https://openalex.org/W4220959278","https://openalex.org/W4293527381","https://openalex.org/W4296538609","https://openalex.org/W4311361333","https://openalex.org/W4318677156","https://openalex.org/W4385519223","https://openalex.org/W4386389488","https://openalex.org/W4386524296","https://openalex.org/W4388806745","https://openalex.org/W4388857826","https://openalex.org/W4392209940","https://openalex.org/W4398152742","https://openalex.org/W4399900751","https://openalex.org/W4401398757","https://openalex.org/W4403210624","https://openalex.org/W4404201390","https://openalex.org/W6674330103","https://openalex.org/W6863513881","https://openalex.org/W6867580348","https://openalex.org/W6871663222","https://openalex.org/W6872184113"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W4298170800","https://openalex.org/W2895890526","https://openalex.org/W617692174","https://openalex.org/W2794758919","https://openalex.org/W4232781930","https://openalex.org/W1913642778","https://openalex.org/W2630858571","https://openalex.org/W4300860228","https://openalex.org/W2329406070"],"abstract_inverted_index":{"Emotion":[0],"recognition":[1,309,395],"in":[2,14,50,310,396],"speech":[3,16,70,172,197],"is":[4,159],"essential":[5],"for":[6,68,363,392],"enhancing":[7,92],"human-computer":[8],"interaction":[9],"(HCI)":[10],"systems.":[11],"Despite":[12],"progress":[13],"Bangla":[15,69,311,397],"emotion":[17,71,291,308,394],"recognition,":[18,72],"challenges":[19],"remain,":[20],"including":[21,107],"low":[22],"accuracy,":[23],"speaker":[24],"dependency,":[25],"and":[26,48,96,129,226,259,282,288,328,340,361,369,372],"poor":[27],"generalization":[28],"across":[29,293],"emotional":[30,179,240],"expressions.":[31],"Previous":[32],"approaches":[33],"often":[34],"rely":[35],"on":[36],"traditional":[37],"machine":[38],"learning":[39,43,64,187,263,304,391],"or":[40,52],"basic":[41],"deep":[42,63,186,279,386],"models,":[44,254],"struggling":[45],"with":[46,82,221,232,264,319,354,385],"robustness":[47,95,289],"accuracy":[49,287],"noisy":[51],"varied":[53],"data.":[54],"In":[55],"this":[56],"study,":[57],"we":[58,182,255],"propose":[59],"a":[60,101,184,265,314,329],"novel":[61],"multi-stream":[62,185],"feature":[65],"fusion":[66,275],"approach":[67,80],"addressing":[73],"the":[74,89,93,171,178,196,206,216,227,271,286,299,344,364,379],"limitations":[75],"of":[76,104,141,170,195,202,252,276,290,301,332,346,356,381],"existing":[77,320],"methods.":[78,321],"Our":[79,296,349],"begins":[81],"various":[83,303],"data":[84],"augmentation":[85],"techniques":[86],"applied":[87],"to":[88,162,189,269,306,342],"training":[90],"dataset,":[91],"model's":[94],"generalization.":[97],"We":[98,322],"then":[99,260],"extract":[100],"comprehensive":[102,316],"set":[103],"handcrafted":[105,243,277,383],"features,":[106,278,281],"Zero-Crossing":[108],"Rate":[109],"(ZCR),":[110],"chromagram,":[111,149],"spectral":[112,114,116,118],"centroid,":[113],"roll-off,":[115],"contrast,":[117],"flatness,":[119],"Mel-Frequency":[120],"Cepstral":[121],"Coefficients":[122],"(MFCCs),":[123],"Root":[124],"Mean":[125],"Square":[126],"(RMS)":[127],"energy,":[128],"Mel-spectrogram.":[130],"Although":[131],"these":[132,253],"features":[133,166,244,384,388],"are":[134,143],"used":[135],"as":[136,156,335],"1D":[137,210,219,230],"numerical":[138],"vectors,":[139],"some":[140],"them":[142],"computed":[144],"from":[145],"time-frequency":[146],"representations":[147,194],"(e.g.,":[148],"Mel-spectrogram)":[150],"that":[151,242],"can":[152],"themselves":[153],"be":[154],"depicted":[155],"images,":[157],"which":[158],"conceptually":[160],"close":[161],"imaging-based":[163],"analysis.":[164],"These":[165,236,376],"capture":[167,238],"key":[168],"characteristics":[169],"signal,":[173],"providing":[174,313],"valuable":[175],"insights":[176],"into":[177],"content.":[180],"Sequentially,":[181],"utilize":[183,323],"architecture":[188,200],"automatically":[190],"learn":[191],"complex,":[192],"hierarchical":[193],"signal.":[198],"This":[199,274],"consists":[201],"three":[203,324],"distinct":[204],"streams:":[205],"first":[207],"stream":[208],"uses":[209],"convolutional":[211],"neural":[212],"networks":[213],"(1D":[214],"CNNs),":[215],"second":[217],"integrates":[218],"CNN":[220],"Long":[222],"Short-Term":[223],"Memory":[224],"(LSTM),":[225],"third":[228],"combines":[229],"CNNs":[231],"bidirectional":[233],"LSTM":[234],"(Bi-LSTM).":[235],"models":[237,305],"intricate":[239],"nuances":[241],"alone":[245],"may":[246],"not":[247],"fully":[248],"represent.":[249],"For":[250],"each":[251],"generate":[256],"predicted":[257],"scores":[258],"employ":[261],"ensemble":[262,283,390],"soft":[266],"voting":[267,284],"technique":[268],"produce":[270],"final":[272],"prediction.":[273],"learning-derived":[280],"enhances":[285],"identification":[292],"multiple":[294],"datasets.":[295],"method":[297,350],"demonstrates":[298],"effectiveness":[300,380],"combining":[302,382],"improve":[307],"speech,":[312],"more":[315],"solution":[317],"compared":[318],"primary":[325],"datasets-SUBESCO,":[326],"BanglaSER,":[327,366,370],"merged":[330,367],"version":[331],"both-as":[333],"well":[334],"two":[336],"external":[337],"datasets,":[338,374],"RAVDESS":[339],"EMODB,":[341],"assess":[343],"performance":[345],"our":[347],"models.":[348],"achieves":[351],"impressive":[352],"results":[353,377],"accuracies":[355],"92.90%,":[357],"85.20%,":[358],"90.63%,":[359],"67.71%,":[360],"69.25%":[362],"SUBESCO,":[365],"SUBESCO":[368],"RAVDESS,":[371],"EMODB":[373],"respectively.":[375],"demonstrate":[378],"learning-based":[387],"through":[389],"robust":[393],"speech.":[398]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
