{"id":"https://openalex.org/W3207733014","doi":"https://doi.org/10.1145/3475957.3484448","title":"Fusion of Acoustic and Linguistic Information using Supervised Autoencoder for Improved Emotion Recognition","display_name":"Fusion of Acoustic and Linguistic Information using Supervised Autoencoder for Improved Emotion Recognition","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3207733014","doi":"https://doi.org/10.1145/3475957.3484448","mag":"3207733014"},"language":"en","primary_location":{"id":"doi:10.1145/3475957.3484448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475957.3484448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge","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/A5087200921","display_name":"Bogdan Vlasenko","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bogdan Vlasenko","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000985806","display_name":"RaviShankar Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"RaviShankar Prasad","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.8374,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86368159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"59"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9955999851226807,"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/autoencoder","display_name":"Autoencoder","score":0.8032557964324951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6708167791366577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244129538536072},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.617047131061554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5888436436653137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5589258670806885},{"id":"https://openalex.org/keywords/information-fusion","display_name":"Information fusion","score":0.5262289047241211},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.4529499113559723},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4163317084312439},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3744209408760071},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2002786099910736}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8032557964324951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6708167791366577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244129538536072},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.617047131061554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5888436436653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5589258670806885},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.5262289047241211},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.4529499113559723},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4163317084312439},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3744209408760071},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2002786099910736},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3475957.3484448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3475957.3484448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd on Multimodal Sentiment Analysis Challenge","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2043632943","https://openalex.org/W2085662862","https://openalex.org/W2125462608","https://openalex.org/W2239141610","https://openalex.org/W2400604769","https://openalex.org/W2406311945","https://openalex.org/W2518110751","https://openalex.org/W2610961739","https://openalex.org/W2750852530","https://openalex.org/W2803098682","https://openalex.org/W2890732907","https://openalex.org/W2936879941","https://openalex.org/W2950182411","https://openalex.org/W2962770129","https://openalex.org/W2963341956","https://openalex.org/W2963614358","https://openalex.org/W2985276180","https://openalex.org/W3003908700","https://openalex.org/W3094918372","https://openalex.org/W3097075955","https://openalex.org/W3099782249","https://openalex.org/W3152478832","https://openalex.org/W3153807302","https://openalex.org/W3163571928","https://openalex.org/W3163767300","https://openalex.org/W3196215173","https://openalex.org/W3196761683","https://openalex.org/W4287389467"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2312116756","https://openalex.org/W2388612579","https://openalex.org/W4296068813","https://openalex.org/W2392793229","https://openalex.org/W2361928421","https://openalex.org/W2348824220","https://openalex.org/W3080440950","https://openalex.org/W2347652535","https://openalex.org/W2914836171"],"abstract_inverted_index":{"Automatic":[0],"recognition":[1,134],"of":[2,9,18,28,102,110,157,186,195,221,231,257],"human":[3,19,55],"emotion":[4,85,133],"has":[5,12],"a":[6,193],"wide":[7],"range":[8,156],"applications":[10],"and":[11,64,80,115,129,145,159,165,188,200,223,233,259],"always":[13],"attracted":[14],"increasing":[15],"attention.":[16],"Expressions":[17],"emotions":[20,56,111],"can":[21],"apparently":[22],"be":[23],"identified":[24],"across":[25,77],"different":[26,123,147],"modalities":[27,61],"communication,":[29],"such":[30],"as":[31],"speech,":[32],"text,":[33],"mimics,":[34],"etc.":[35],"The":[36,69,87,100,136],"\"Multimodal":[37],"Sentiment":[38],"Analysis":[39],"in":[40,97,192,198],"Real-life":[41],"Media'":[42],"(MuSe)":[43],"2021":[44],"challenge":[45,70],"provides":[46],"an":[47],"environment":[48],"to":[49,53,72,106,125,151,241],"develop":[50],"new":[51],"techniques":[52,226],"recognize":[54],"or":[57],"sentiments":[58],"using":[59],"multiple":[60],"(audio,":[62],"video,":[63],"text)":[65],"over":[66,248],"in-the-wild":[67],"data.":[68],"encourages":[71],"jointly":[73],"model":[74],"the":[75,94,98,103,113,119,176,249,264],"information":[76,131],"audio,":[78],"video":[79],"text":[81,260],"modalities,":[82,144],"for":[83,132,174],"improving":[84],"recognition.":[86],"present":[88],"paper":[89,181],"describes":[90],"our":[91],"attempt":[92],"towards":[93],"MuSe-Sent":[95],"task":[96],"challenge.":[99],"goal":[101],"sub-challenge":[104],"is":[105],"perform":[107],"turn-level":[108],"prediction":[109],"within":[112],"arousal":[114,199],"valence":[116,201],"dimensions.":[117,202],"In":[118,179],"paper,":[120],"we":[121,182],"investigate":[122],"approaches":[124],"optimally":[126],"fuse":[127],"linguistic":[128,160,234],"acoustic":[130,158,168,190,232,258],"systems.":[135],"proposed":[137,250],"systems":[138],"employ":[139],"features":[140,161,191],"derived":[141],"from":[142],"these":[143],"uses":[146],"deep":[148],"learning":[149],"architectures":[150],"explore":[152],"their":[153],"cross-dependencies.":[154],"Wide":[155],"provided":[162],"by":[163],"organizers":[164],"recently":[166],"established":[167],"embedding":[169],"wav2vec":[170],"2.0":[171],"are":[172],"used":[173],"modeling":[175,230],"inherent":[177],"emotions.":[178],"this":[180],"compare":[183],"discriminative":[184],"characteristics":[185],"hand-crafted":[187],"data-driven":[189],"context":[194],"emotional":[196],"classification":[197,225,238],"Ensemble":[203],"based":[204,261],"classifiers":[205],"were":[206],"compared":[207,240],"with":[208,214],"advanced":[209],"supervised":[210],"autoendcoder":[211],"(SAE)":[212],"technique":[213],"Bayesian":[215],"Optimizer":[216],"hyperparameter":[217],"tuning":[218],"approach.":[219],"Comparison":[220],"uni-":[222],"bi-modal":[224],"showed":[227],"that":[228],"joint":[229],"cues":[235],"could":[236],"improve":[237],"performance":[239],"individual":[242],"modalities.":[243],"Experimental":[244],"results":[245],"show":[246],"improvement":[247],"baseline":[251],"system,":[252],"which":[253],"focuses":[254],"on":[255,263],"fusion":[256],"information,":[262],"test":[265],"set":[266],"evaluation.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}