{"id":"https://openalex.org/W4406702577","doi":"https://doi.org/10.1145/3705927.3705939","title":"A Time-Distributed CNN-LSTM with Attention Model for Speech Based Emotion Recognition","display_name":"A Time-Distributed CNN-LSTM with Attention Model for Speech Based Emotion Recognition","publication_year":2024,"publication_date":"2024-11-08","ids":{"openalex":"https://openalex.org/W4406702577","doi":"https://doi.org/10.1145/3705927.3705939"},"language":"en","primary_location":{"id":"doi:10.1145/3705927.3705939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3705927.3705939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Digital Medicine and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111671511","display_name":"Kedar Deshpande","orcid":"https://orcid.org/0009-0001-4643-8708"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kedar Deshpande","raw_affiliation_strings":["IIIT Bangalore, Bengaluru, India,"],"raw_orcid":"https://orcid.org/0009-0001-4643-8708","affiliations":[{"raw_affiliation_string":"IIIT Bangalore, Bengaluru, India,","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025052689","display_name":"Manjit Singh Sodhi","orcid":"https://orcid.org/0009-0004-8352-472X"},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manjit Singh Sodhi","raw_affiliation_strings":["IBM Bangalore, Bengaluru, India,"],"raw_orcid":"https://orcid.org/0009-0004-8352-472X","affiliations":[{"raw_affiliation_string":"IBM Bangalore, Bengaluru, India,","institution_ids":["https://openalex.org/I4210129961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115983643","display_name":"Nidhi Raniyer","orcid":"https://orcid.org/0009-0000-7538-895X"},"institutions":[{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nidhi Raniyer","raw_affiliation_strings":["IBM Bangalore, Bengaluru, India,"],"raw_orcid":"https://orcid.org/0009-0000-7538-895X","affiliations":[{"raw_affiliation_string":"IBM Bangalore, Bengaluru, India,","institution_ids":["https://openalex.org/I4210129961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061397479","display_name":"Madhav Rao","orcid":"https://orcid.org/0000-0003-2278-9148"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhav Rao","raw_affiliation_strings":["IIIT Bangalore, Bengaluru, India,"],"raw_orcid":"https://orcid.org/0000-0003-2278-9148","affiliations":[{"raw_affiliation_string":"IIIT Bangalore, Bengaluru, India,","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7301,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7503699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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":0.9991999864578247,"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":0.996999979019165,"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/T10057","display_name":"Face and Expression Recognition","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7971407175064087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.683972179889679},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6830576658248901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4303659498691559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971407175064087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.683972179889679},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6830576658248901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4303659498691559}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3705927.3705939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3705927.3705939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 7th International Conference on Digital Medicine and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2183159415","https://openalex.org/W2579766263","https://openalex.org/W2768041052","https://openalex.org/W2964370293","https://openalex.org/W3082528453","https://openalex.org/W3119263922","https://openalex.org/W3127521573","https://openalex.org/W3144907487","https://openalex.org/W3158929093","https://openalex.org/W3178599867","https://openalex.org/W3186192207","https://openalex.org/W3213879871","https://openalex.org/W3217453706","https://openalex.org/W4210355938","https://openalex.org/W4210777104","https://openalex.org/W4310154196","https://openalex.org/W4313254214","https://openalex.org/W4313316128","https://openalex.org/W4367310744","https://openalex.org/W4377971642","https://openalex.org/W4382008945","https://openalex.org/W4382316601","https://openalex.org/W4385756532","https://openalex.org/W4391620705","https://openalex.org/W4392397327","https://openalex.org/W4392822744","https://openalex.org/W4392903514"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Emotion":[0,48],"recognition":[1,32,75],"is":[2,49,96,223],"expected":[3],"to":[4,87,125,153,167,180,202,228,250],"play":[5],"a":[6,81,137,143,194,199,217],"critical":[7],"role":[8],"in":[9,16,52],"improving":[10],"user":[11],"experiences":[12],"for":[13,105,244],"digital":[14],"products":[15],"the":[17,25,41,127,158,172,188,204,210,251],"near":[18],"future.":[19],"In":[20],"this":[21],"context,":[22],"most":[23],"of":[24,119,140,145,187,209,220],"past":[26],"work":[27,72],"has":[28],"emphasized":[29],"on":[30,98,234],"emotion":[31,74,90],"through":[33,76],"images":[34],"or":[35],"video":[36],"streams,":[37],"whereas":[38],"only":[39],"recently":[40],"other":[42,229],"modalities":[43],"have":[44],"come":[45],"into":[46,207],"prominence.":[47],"generally":[50],"conceived":[51],"multi-modal":[53],"forms":[54],"which":[55,101,147,222],"primarily":[56],"includes":[57],"facial":[58],"expressions,":[59],"hand":[60],"movements,":[61],"spoken":[62],"words,":[63],"and":[64,69,116,156,198,247,253],"its":[65],"associated":[66],"tone,":[67],"intensity,":[68],"speed.":[70],"This":[71],"proposes":[73],"audio":[77,92,103,121,132,205],"snippets.":[78],"We":[79],"propose":[80],"2D":[82,162],"CNN-LSTM":[83],"with":[84,142],"attention":[85,192],"model":[86,95,189,215,238],"accurately":[88],"predict":[89],"from":[91,171],"stream.":[93],"The":[94,184,213,237],"trained":[97,233],"RAVDESS":[99,235],"dataset":[100],"contains":[102],"files":[104,239],"8":[106,211],"emotions":[107],"including":[108],"Happy,":[109],"Calm,":[110],"Neutral,":[111],"Sad,":[112],"Fear,":[113],"Disgust,":[114],"Surprise":[115],"Angry.":[117],"Mel-Spectrogram":[118,130],"each":[120],"signal":[122],"was":[123,134,148],"used":[124,166],"train":[126],"model.":[128,159],"Each":[129],"representing":[131],"stream,":[133],"framed":[135],"using":[136],"window":[138],"size":[139],"128,":[141],"stride":[144],"64,":[146],"then":[149],"supplied":[150],"as":[151],"inputs":[152],"train,":[154],"validate":[155],"test":[157,218],"Three":[160],"Time-Distributed":[161],"CNN":[163],"blocks":[164],"were":[165],"extract":[168,181],"implicit":[169],"features":[170],"windowed":[173],"spectrogram,":[174],"followed":[175],"by":[176],"an":[177,191],"LSTM":[178],"layer":[179,197,201],"temporal":[182],"properties.":[183],"final":[185],"parts":[186],"involve":[190],"layer,":[193],"fully":[195],"connected":[196],"softmax":[200],"classify":[203],"stream":[206],"one":[208],"classes.":[212],"proposed":[214],"achieved":[216],"accuracy":[219],"84%":[221],"far":[224],"superior":[225],"when":[226],"compared":[227],"state-of-the-art":[230],"(SOTA)":[231],"models":[232],"dataset.":[236],"are":[240],"made":[241],"freely":[242],"available":[243],"further":[245],"usage":[246],"easy":[248],"adoption":[249],"researchers":[252],"developers\u2019":[254],"community.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}