{"id":"https://openalex.org/W3015308237","doi":"https://doi.org/10.1109/icassp40776.2020.9054580","title":"Speaker-Invariant Affective Representation Learning via Adversarial Training","display_name":"Speaker-Invariant Affective Representation Learning via Adversarial Training","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015308237","doi":"https://doi.org/10.1109/icassp40776.2020.9054580","mag":"3015308237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5101654853","display_name":"Haoqi Li","orcid":"https://orcid.org/0000-0002-8851-4529"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoqi Li","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["JD AI Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Mountain View, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017130874","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0001-8804-7150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["JD AI Research, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"JD AI Research, Mountain View, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021678540","display_name":"Panayiotis Georgiou","orcid":"https://orcid.org/0000-0002-0790-7161"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panayiotis Georgiou","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101654853"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":7.0048,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97410428,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7144","last_page":"7148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9976999759674072,"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":0.7590184211730957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6872462034225464},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6659125089645386},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5697423219680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5507944822311401},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4844534397125244},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4599842429161072},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4533202350139618},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44824087619781494},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.42416155338287354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4193590581417084},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10946452617645264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590184211730957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6872462034225464},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6659125089645386},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5697423219680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5507944822311401},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4844534397125244},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4599842429161072},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4533202350139618},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44824087619781494},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.42416155338287354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4193590581417084},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10946452617645264},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1568716973","https://openalex.org/W1731081199","https://openalex.org/W2085628288","https://openalex.org/W2099471712","https://openalex.org/W2117274752","https://openalex.org/W2126672039","https://openalex.org/W2146334809","https://openalex.org/W2165871906","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2510867321","https://openalex.org/W2512449761","https://openalex.org/W2585174249","https://openalex.org/W2587088898","https://openalex.org/W2598545578","https://openalex.org/W2625426967","https://openalex.org/W2796339975","https://openalex.org/W2801581493","https://openalex.org/W2803098682","https://openalex.org/W2808456396","https://openalex.org/W2883409523","https://openalex.org/W2889065492","https://openalex.org/W2889445231","https://openalex.org/W2913340405","https://openalex.org/W2925037031","https://openalex.org/W2936372954","https://openalex.org/W2936451900","https://openalex.org/W2945328857","https://openalex.org/W2962993399","https://openalex.org/W2963130397","https://openalex.org/W2963447013","https://openalex.org/W2963569749","https://openalex.org/W2972943112","https://openalex.org/W2973034847","https://openalex.org/W2973157397","https://openalex.org/W4320013936","https://openalex.org/W6637618735","https://openalex.org/W6714031499","https://openalex.org/W6739009451","https://openalex.org/W6750258553","https://openalex.org/W6760803314","https://openalex.org/W6762753787"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2353179089","https://openalex.org/W4310988119","https://openalex.org/W4285226279"],"abstract_inverted_index":{"Representation":[0],"learning":[1,46],"for":[2],"speech":[3,27,50,62,118],"emotion":[4,36,51,73,119],"recognition":[5],"is":[6,22,104],"challenging":[7],"due":[8],"to":[9,48,67,81,97,124],"labeled":[10],"data":[11],"sparsity":[12],"issue":[13],"and":[14,35,109,121],"lack":[15],"of":[16,32,57],"gold-standard":[17],"references.":[18],"In":[19,39],"addition,":[20],"there":[21],"much":[23],"variability":[24,59],"from":[25,72],"input":[26],"signals,":[28],"human":[29],"subjective":[30],"perception":[31],"the":[33,55,61,69,88],"signals":[34],"label":[37],"ambiguity.":[38],"this":[40],"paper,":[41],"we":[42,65],"propose":[43,66],"a":[44],"machine":[45],"framework":[47],"obtain":[49],"representations":[52],"by":[53],"limiting":[54],"effect":[56],"speaker":[58,70,100],"in":[60,79],"signals.":[63],"Specifically":[64],"disentangle":[68],"characteristics":[71],"through":[74],"an":[75,93],"adversarial":[76],"training":[77],"network":[78],"order":[80],"better":[82],"represent":[83],"emotion.":[84],"Our":[85,102],"method":[86,116],"combines":[87],"gradient":[89],"reversal":[90],"technique":[91],"with":[92],"entropy":[94],"loss":[95],"function":[96],"remove":[98],"such":[99],"information.":[101],"approach":[103],"evaluated":[105],"on":[106],"both":[107],"IEMOCAP":[108],"CMU-MOSEI":[110],"datasets.":[111],"We":[112],"show":[113],"that":[114],"our":[115],"improves":[117],"classification":[120],"increases":[122],"generalization":[123],"unseen":[125],"speakers.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}