{"id":"https://openalex.org/W4297510487","doi":"https://doi.org/10.1145/3551876.3554801","title":"Transformer-based Non-Verbal Emotion Recognition","display_name":"Transformer-based Non-Verbal Emotion Recognition","publication_year":2022,"publication_date":"2022-09-28","ids":{"openalex":"https://openalex.org/W4297510487","doi":"https://doi.org/10.1145/3551876.3554801"},"language":"en","primary_location":{"id":"doi:10.1145/3551876.3554801","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551876.3554801","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551876.3554801","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3551876.3554801","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082357372","display_name":"Lorenzo Vaiani","orcid":"https://orcid.org/0000-0002-3605-1577"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Vaiani","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001746215","display_name":"Luca Cagliero","orcid":"https://orcid.org/0000-0002-7185-5247"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cagliero","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074057809","display_name":"Paolo Garza","orcid":"https://orcid.org/0000-0002-1263-7522"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Garza","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.1925,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58171303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.7255734205245972},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6182579398155212},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5934672951698303},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5844706296920776},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.5517322421073914},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5270441174507141},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46385976672172546},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44057950377464294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40385451912879944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3330293893814087},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16524630784988403},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11015933752059937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7255734205245972},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6182579398155212},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5934672951698303},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5844706296920776},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.5517322421073914},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5270441174507141},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46385976672172546},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44057950377464294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40385451912879944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3330293893814087},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16524630784988403},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11015933752059937},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551876.3554801","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551876.3554801","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551876.3554801","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3551876.3554801","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551876.3554801","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551876.3554801","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297510487.pdf","grobid_xml":"https://content.openalex.org/works/W4297510487.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2146334809","https://openalex.org/W2148822124","https://openalex.org/W2785952417","https://openalex.org/W2796768192","https://openalex.org/W2802646883","https://openalex.org/W2914304175","https://openalex.org/W2935542736","https://openalex.org/W2938004196","https://openalex.org/W2969889150","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2981687423","https://openalex.org/W3015213852","https://openalex.org/W3016011332","https://openalex.org/W3026744663","https://openalex.org/W3032735579","https://openalex.org/W3144810982","https://openalex.org/W3158929093","https://openalex.org/W3162391496","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210616249","https://openalex.org/W4221145109","https://openalex.org/W4254718357","https://openalex.org/W4281492411","https://openalex.org/W4286800002","https://openalex.org/W4293115660","https://openalex.org/W4297808394","https://openalex.org/W4300948910","https://openalex.org/W4304098636","https://openalex.org/W4307539136","https://openalex.org/W6929262754"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Recognizing":[0],"emotions":[1],"in":[2,95],"non-verbal":[3,60,119],"audio":[4,51,70],"tracks":[5],"requires":[6],"a":[7,45],"deep":[8],"understanding":[9],"of":[10,28,44,68,118],"their":[11],"underlying":[12],"features.":[13],"Traditional":[14],"classifiers":[15],"relying":[16],"on":[17,49,76],"excitation,":[18],"prosodic,":[19],"and":[20],"vocal":[21],"traction":[22],"features":[23],"are":[24],"not":[25],"always":[26],"capable":[27],"effectively":[29],"generalizing":[30],"across":[31,82],"speakers'":[32,83],"genders.":[33,84],"In":[34],"the":[35,42,66,77,96,108,116],"ComParE":[36],"2022":[37],"vocalisation":[38],"sub-challenge":[39],"we":[40],"explore":[41],"use":[43],"Transformer":[46],"architecture":[47],"trained":[48],"contrastive":[50],"examples.":[52],"We":[53,63],"leverage":[54],"augmented":[55],"data":[56],"to":[57,80],"learn":[58],"robust":[59],"emotion":[61,120],"classifiers.":[62],"also":[64],"investigate":[65],"impact":[67],"different":[69],"transformations,":[71],"including":[72],"neural":[73,90],"voice":[74,91],"conversion,":[75],"classifier":[78],"capability":[79],"generalize":[81],"The":[85],"empirical":[86],"findings":[87],"indicate":[88],"that":[89],"conversion":[92],"is":[93,105],"beneficial":[94],"pretraining":[97],"phase,":[98],"yielding":[99],"an":[100],"improved":[101],"model":[102,113],"generality,":[103],"whereas":[104],"harmful":[106],"at":[107],"finetuning":[109],"stage":[110],"as":[111],"hinders":[112],"specialization":[114],"for":[115],"task":[117],"recognition.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}