{"id":"https://openalex.org/W3162811262","doi":"https://doi.org/10.1109/icassp39728.2021.9413910","title":"Contrastive Unsupervised Learning for Speech Emotion Recognition","display_name":"Contrastive Unsupervised Learning for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162811262","doi":"https://doi.org/10.1109/icassp39728.2021.9413910","mag":"3162811262"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100355202","display_name":"Mao Li","orcid":"https://orcid.org/0000-0002-5964-1764"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mao Li","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101859168","display_name":"Bo Yang","orcid":"https://orcid.org/0000-0002-4288-8349"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Yang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053202754","display_name":"Joshua Levy","orcid":"https://orcid.org/0000-0001-8050-1291"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Levy","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091009689","display_name":"Viktor Rozgi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor Rozgic","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034173999","display_name":"Spyros Matsoukas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spyros Matsoukas","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076143510","display_name":"Constantinos Papayiannis","orcid":"https://orcid.org/0000-0001-6448-3767"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Constantinos Papayiannis","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137710","display_name":"Daniel Bone","orcid":"https://orcid.org/0000-0002-7288-0786"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Bone","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406950","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-1560-6182"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6329","last_page":"6333"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7658392190933228},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.7255392670631409},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5362768769264221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5307345986366272},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5193668007850647},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.44771307706832886},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.42998117208480835},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42724621295928955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37608614563941956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3424733877182007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3252027928829193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09198415279388428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658392190933228},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.7255392670631409},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5362768769264221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307345986366272},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5193668007850647},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.44771307706832886},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.42998117208480835},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42724621295928955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37608614563941956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3424733877182007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3252027928829193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09198415279388428},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1964469912","https://openalex.org/W2071712938","https://openalex.org/W2075953807","https://openalex.org/W2146334809","https://openalex.org/W2170876097","https://openalex.org/W2313339984","https://openalex.org/W2399733683","https://openalex.org/W2576530755","https://openalex.org/W2742542661","https://openalex.org/W2800126857","https://openalex.org/W2803098682","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2900358852","https://openalex.org/W2946006146","https://openalex.org/W2949759968","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2973042454","https://openalex.org/W2981022124","https://openalex.org/W3030163527","https://openalex.org/W3035524453","https://openalex.org/W4292779060","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6731509202","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6762796984","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W2129455854","https://openalex.org/W3204853141"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,61,78],"recognition":[2,62],"(SER)":[3],"is":[4],"a":[5,20],"key":[6],"technology":[7],"to":[8,98],"enable":[9],"more":[10],"natural":[11],"human-machine":[12],"communication.":[13],"However,":[14],"SER":[15],"has":[16],"long":[17],"suffered":[18],"from":[19,56],"lack":[21],"of":[22],"public":[23],"large-scale":[24],"labeled":[25],"datasets.":[26],"To":[27],"circumvent":[28],"this":[29,67],"problem,":[30],"we":[31],"investigate":[32],"how":[33],"unsupervised":[34],"representation":[35],"learning":[36],"on":[37,84,87],"unlabeled":[38,57],"datasets":[39],"can":[40,52],"benefit":[41],"SER.":[42],"We":[43],"show":[44],"that":[45],"the":[46,88],"contrastive":[47],"predictive":[48],"coding":[49],"(CPC)":[50],"method":[51,68,92],"learn":[53],"salient":[54],"representations":[55],"datasets,":[58],"which":[59],"improves":[60],"performance.":[63],"In":[64],"our":[65,91],"experiments,":[66],"achieved":[69],"state-of-the-art":[70],"concordance":[71],"correlation":[72],"coefficient":[73],"(CCC)":[74],"performance":[75,95],"for":[76],"all":[77],"primitives":[79],"(activation,":[80],"valence,":[81],"and":[82],"dominance)":[83],"IEMOCAP.":[85],"Additionally,":[86],"MSP-Podcast":[89],"dataset,":[90],"obtained":[93],"considerable":[94],"improvements":[96],"compared":[97],"baselines.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
