{"id":"https://openalex.org/W4405429477","doi":"https://doi.org/10.1109/access.2024.3517733","title":"CochleaSpecNet: An Attention Based Dual Branch Hybrid CNN-GRU Network for Speech Emotion Recognition Using Cochleagram and Spectrogram","display_name":"CochleaSpecNet: An Attention Based Dual Branch Hybrid CNN-GRU Network for Speech Emotion Recognition Using Cochleagram and Spectrogram","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4405429477","doi":"https://doi.org/10.1109/access.2024.3517733"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3517733","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517733","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3517733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098776644","display_name":"Atkia Namey","orcid":null},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Atkia Anika Namey","raw_affiliation_strings":["Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012667733","display_name":"Khadija Akter","orcid":"https://orcid.org/0009-0007-6076-2866"},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Khadija Akter","raw_affiliation_strings":["Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020909684","display_name":"Md. Azad Hossain","orcid":"https://orcid.org/0000-0002-8251-5168"},"institutions":[{"id":"https://openalex.org/I102782458","display_name":"Chittagong University of Engineering & Technology","ror":"https://ror.org/052qsay17","country_code":"BD","type":"education","lineage":["https://openalex.org/I102782458"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Azad Hossain","raw_affiliation_strings":["Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-8251-5168","affiliations":[{"raw_affiliation_string":"Dept. of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh","institution_ids":["https://openalex.org/I102782458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089476507","display_name":"M. Ali Akber Dewan","orcid":"https://orcid.org/0000-0001-6347-7509"},"institutions":[{"id":"https://openalex.org/I86897205","display_name":"Athabasca University","ror":"https://ror.org/01y3xgc52","country_code":"CA","type":"education","lineage":["https://openalex.org/I86897205"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"M. Ali Akber Dewan","raw_affiliation_strings":["Faculty of Science and Technology, School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0001-6347-7509","affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, School of Computing and Information Systems, Athabasca University, Athabasca, AB, Canada","institution_ids":["https://openalex.org/I86897205"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":1.0214,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75830424,"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":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8978999853134155,"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":0.8978999853134155,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.823199987411499,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/spectrogram","display_name":"Spectrogram","score":0.8971869945526123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7364858984947205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145043015480042},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6660805344581604},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4479120969772339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44236642122268677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4055572748184204},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0601348876953125}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8971869945526123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7364858984947205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145043015480042},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6660805344581604},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4479120969772339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44236642122268677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4055572748184204},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0601348876953125},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3517733","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517733","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bae9b6a16ad24a0e9cc60b6481f74417","is_oa":true,"landing_page_url":"https://doaj.org/article/bae9b6a16ad24a0e9cc60b6481f74417","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":"IEEE Access, Vol 12, Pp 190760-190774 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3517733","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3517733","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1523719202","https://openalex.org/W2153720647","https://openalex.org/W2803427263","https://openalex.org/W2889717020","https://openalex.org/W2892071465","https://openalex.org/W2963569749","https://openalex.org/W2998064461","https://openalex.org/W3038993799","https://openalex.org/W3081192838","https://openalex.org/W3094273504","https://openalex.org/W3095612572","https://openalex.org/W3112103486","https://openalex.org/W3115394420","https://openalex.org/W3124875196","https://openalex.org/W3126625480","https://openalex.org/W3144907487","https://openalex.org/W3178599867","https://openalex.org/W3181187515","https://openalex.org/W3191181235","https://openalex.org/W3209572141","https://openalex.org/W4205102344","https://openalex.org/W4205131079","https://openalex.org/W4220754084","https://openalex.org/W4220959278","https://openalex.org/W4283711157","https://openalex.org/W4284899427","https://openalex.org/W4296523924","https://openalex.org/W4312464486","https://openalex.org/W4361731443","https://openalex.org/W4366377470","https://openalex.org/W4387712775","https://openalex.org/W4390071599","https://openalex.org/W4392209718","https://openalex.org/W4398249819","https://openalex.org/W6853970758"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1923358586","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Being":[0],"one":[1],"of":[2,15,30,114,138,156,180,199,210,242,248,267,283],"the":[3,12,28,41,82,112,125,157,163,173,197,200,219,240,249,274,281,284],"main":[4],"communication":[5],"medium,":[6],"speech":[7,79,299],"contains":[8],"necessary":[9],"information":[10],"about":[11],"emotional":[13,43],"state":[14,44],"a":[16,31,66,88,117,135,145,177,245,289],"human.":[17],"Accurate":[18],"emotion":[19,296],"recognition":[20],"is":[21,134,256],"crucial":[22],"for":[23,81,97,292],"enhancing":[24],"human-machine":[25],"interactions,":[26],"highlighting":[27],"importance":[29],"strong":[32],"Speech":[33,167],"Emotion":[34,168],"Recognition":[35],"(SER)":[36],"system.":[37],"SER":[38,68,201,254,286],"system":[39],"classifies":[40],"human":[42],"based":[45,205],"on":[46,162],"speaker\u2019s":[47],"utterances":[48],"in":[49,131,148,171,182,228],"different":[50],"catagories":[51],"such":[52],"as":[53,271],"sad,":[54],"happy,":[55,189],"neutral,":[56,190],"angry,":[57,187],"surprise,":[58,188],"calm":[59,237],"and":[60,73,191,263,294],"so":[61],"on.":[62],"This":[63,222],"research":[64],"introduces":[65],"novel":[67],"approach":[69,291],"that":[70,91,233],"utilizes":[71],"cochleagram":[72],"spectrogram":[74],"features":[75,270],"to":[76,105,110,194,259],"capture":[77],"relevant":[78],"patterns":[80],"classifier":[83],"network.":[84],"The":[85,265],"network":[86,279],"integrates":[87],"hybrid":[89,277],"model":[90,158,174,251],"combines":[92],"Convolutional":[93],"Neural":[94],"Networks":[95],"(CNN)":[96],"feature":[98],"extraction":[99],"with":[100,239,252],"Gated":[101],"Recurrent":[102],"Units":[103],"(GRU)":[104],"handle":[106],"temporal":[107],"dependencies.":[108],"Furthermore,":[109],"improve":[111],"performance":[113,198],"this":[115,153],"network,":[116],"multi-head":[118],"attention":[119,275],"mechanism":[120],"has":[121,159,175,214,224],"been":[122,160,216],"incorporated":[123],"following":[124],"GRU":[126],"layer.":[127],"Despite":[128],"increasing":[129],"interest":[130],"SER,":[132],"there":[133],"notable":[136,178],"lack":[137],"studies":[139],"using":[140],"Bangla":[141],"language":[142,204],"datasets,":[143],"revealing":[144],"significant":[146],"gap":[147],"current":[149],"research.":[150],"To":[151],"address":[152],"gap,":[154],"evaluation":[155],"conducted":[161],"augmented":[164],"BanglaSER":[165],"(Bangla":[166],"Recognition)":[169],"dataset":[170,213],"which":[172],"achieved":[176],"accuracy":[179,227],"92.04%":[181],"categorizing":[183],"five":[184],"distinct":[185],"emotions:":[186],"sad.":[192],"Additionally,":[193],"further":[195],"evaluate":[196],"model,":[202],"English":[203],"RAVDESS":[206],"(Ryerson":[207],"Audio-Visual":[208],"Database":[209],"Emotional":[211],"Speech)":[212],"also":[215],"employed":[217],"into":[218,273],"proposed":[220,250,285],"model.":[221],"attempt":[223],"provided":[225],"82.40%":[226],"classifying":[229],"eight":[230],"diverse":[231],"emotions":[232,241],"includes":[234],"fear,":[235],"disgust,":[236],"along":[238],"BanglaSER.":[243],"Moreover,":[244],"comparative":[246],"analysis":[247],"existing":[253],"approaches":[255],"carried":[257],"out":[258],"demonstrate":[260],"it\u2019s":[261],"stability":[262],"robustness.":[264],"incorporation":[266],"two":[268],"individual":[269],"inputs":[272],"guided":[276],"neural":[278],"showcases":[280],"efficacy":[282],"system,":[287],"offering":[288],"promising":[290],"precise":[293],"efficient":[295],"categorization":[297],"from":[298],"signals.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}