{"id":"https://openalex.org/W4312313987","doi":"https://doi.org/10.1109/tcss.2022.3228649","title":"RobinNet: A Multimodal Speech Emotion Recognition System With Speaker Recognition for Social Interactions","display_name":"RobinNet: A Multimodal Speech Emotion Recognition System With Speaker Recognition for Social Interactions","publication_year":2022,"publication_date":"2022-12-26","ids":{"openalex":"https://openalex.org/W4312313987","doi":"https://doi.org/10.1109/tcss.2022.3228649"},"language":"en","primary_location":{"id":"doi:10.1109/tcss.2022.3228649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2022.3228649","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-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/A5058714731","display_name":"Yash Khurana","orcid":"https://orcid.org/0000-0003-1776-6048"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yash Khurana","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India"],"raw_orcid":"https://orcid.org/0000-0003-1776-6048","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038836147","display_name":"Swamita Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swamita Gupta","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112395503","display_name":"R. Sathyaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"R. Sathyaraj","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068883308","display_name":"S. P. Raja","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. P. Raja","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India"],"raw_orcid":"https://orcid.org/0000-0002-7216-2207","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0544,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96265422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"11","issue":"1","first_page":"478","last_page":"487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.797021210193634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6246725916862488},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6109264492988586},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.569911539554596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5332567095756531},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4499460756778717},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4483107030391693},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4313663840293884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3276355266571045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.797021210193634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6246725916862488},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6109264492988586},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.569911539554596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332567095756531},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4499460756778717},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4483107030391693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4313663840293884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3276355266571045},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcss.2022.3228649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcss.2022.3228649","pdf_url":null,"source":{"id":"https://openalex.org/S2490693980","display_name":"IEEE Transactions on Computational Social Systems","issn_l":"2329-924X","issn":["2329-924X","2373-7476"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computational Social Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1534131679","https://openalex.org/W1559788381","https://openalex.org/W1566289585","https://openalex.org/W2093428321","https://openalex.org/W2097117768","https://openalex.org/W2164699598","https://openalex.org/W2183341477","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2408520939","https://openalex.org/W2499760652","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2766684614","https://openalex.org/W2890964092","https://openalex.org/W2937584914","https://openalex.org/W2943495380","https://openalex.org/W2946218857","https://openalex.org/W2946690625","https://openalex.org/W2962736520","https://openalex.org/W2962770129","https://openalex.org/W2963800675","https://openalex.org/W2964350391","https://openalex.org/W2970737019","https://openalex.org/W2972463723","https://openalex.org/W2994254596","https://openalex.org/W2995140549","https://openalex.org/W3000086239","https://openalex.org/W3007708573","https://openalex.org/W3012159372","https://openalex.org/W3014475539","https://openalex.org/W3038993799","https://openalex.org/W3048152940","https://openalex.org/W3096262466","https://openalex.org/W3115969014","https://openalex.org/W3120680448","https://openalex.org/W3122349645","https://openalex.org/W3126005225","https://openalex.org/W3135006803","https://openalex.org/W3138022732","https://openalex.org/W3153807302","https://openalex.org/W3169611941","https://openalex.org/W3201068280","https://openalex.org/W3205733239","https://openalex.org/W3207346153","https://openalex.org/W4205734456","https://openalex.org/W4210969683","https://openalex.org/W4220904955","https://openalex.org/W4246244496","https://openalex.org/W4283016277","https://openalex.org/W4285262944","https://openalex.org/W4293519468","https://openalex.org/W4295308310","https://openalex.org/W4304755986","https://openalex.org/W6781638450","https://openalex.org/W6785341548","https://openalex.org/W6810378163"],"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/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"It":[0],"is":[1,31],"essential":[2],"to":[3,15,22,37,73,116,135],"understand":[4],"the":[5,38,44,50,102,118,139,154,172,184,193,225],"underlying":[6],"emotions":[7],"that":[8,183,215],"are":[9],"imparted":[10],"through":[11,91,144,157],"speech":[12,145],"in":[13],"order":[14],"study":[16],"social":[17],"communications":[18],"as":[19,21],"well":[20],"generate":[23],"seamless":[24],"human\u2013computer":[25],"interactions.":[26],"Speech":[27],"emotion":[28,53,142,198],"recognition":[29,143],"(SER)":[30],"a":[32,60,88,112,163],"considerably":[33],"challenging":[34],"task":[35,140],"due":[36],"lack":[39],"of":[40,47,104,141,167,212],"sufficient":[41],"data":[42],"and":[43,52,80,83,109,131,160,202],"complex":[45],"interdependence":[46],"phrases":[48],"with":[49],"context":[51],"they":[54],"imply.":[55],"This":[56,94],"article":[57],"presents":[58],"RobinNet:":[59],"RoBERTa-and":[61],"Inception-ResNet-V2-based":[62],"novel":[63],"multimodal":[64,151,186,197,228],"network":[65,127],"for":[66,78,128,138],"SER.":[67],"The":[68,149,204],"model":[69,115,206],"employs":[70],"transfer":[71,133],"learning":[72,134],"build":[74],"two":[75,155],"unimodal":[76,107],"systems":[77,108],"text":[79],"audio":[81],"features":[82],"then":[84,110],"incorporates":[85],"them":[86],"into":[87],"single":[89],"classifier":[90],"Intermediate":[92],"Fusion.":[93],"work":[95],"has":[96],"been":[97],"created":[98],"after":[99,219],"carefully":[100],"analyzing":[101],"performance":[103],"various":[105],"top-performing":[106],"utilizing":[111],"fine-tuned":[113],"RoBERTa-based":[114],"represent":[117],"textual":[119],"features.":[120],"Furthermore,":[121],"we":[122],"utilize":[123],"an":[124],"Inception-ResNetV2":[125],"pretrained":[126],"Speaker":[129],"Identification":[130],"employ":[132],"train":[136],"it":[137],"using":[146],"spectrogram":[147],"augmentation.":[148],"proposed":[150,185,205],"system":[152,187],"combines":[153],"modalities":[156],"intermediate":[158,208],"fusion":[159,209,218],"gives":[161],"out":[162],"weighted":[164],"accuracy":[165],"(WA)":[166],"72.8%":[168],"when":[169],"evaluated":[170],"against":[171],"interactive":[173],"emotional":[174],"dyadic":[175],"motion":[176],"capture":[177],"(IEMOCAP)":[178],"dataset.":[179],"Experimental":[180],"results":[181],"reveal":[182],"outperforms":[188],"state-of-the-art":[189],"(SOTA)":[190],"solutions":[191],"on":[192],"benchmark":[194],"datasets":[195],"IEMOCAP,":[196],"lines":[199],"dataset":[200],"(MELD),":[201],"CMU-MOSEI.":[203],"utilizes":[207],"unlike":[210],"any":[211],"its":[213],"predecessors":[214],"perform":[216],"late":[217],"significant":[220],"independent":[221],"processing,":[222],"thereby":[223],"improving":[224],"overall":[226],"artificial":[227],"representations.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}