{"id":"https://openalex.org/W4221162793","doi":"https://doi.org/10.1109/icassp43922.2022.9747460","title":"Speaker Normalization for Self-Supervised Speech Emotion Recognition","display_name":"Speaker Normalization for Self-Supervised Speech Emotion Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221162793","doi":"https://doi.org/10.1109/icassp43922.2022.9747460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747460","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5028984453","display_name":"Itai Gat","orcid":"https://orcid.org/0000-0002-3467-9061"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Itai Gat","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100308092","display_name":"Weizhong Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weizhong Zhu","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053864983","display_name":"Ron Hoory","orcid":"https://orcid.org/0009-0006-1327-5160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Hoory","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028984453"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2952,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97745098,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7342","last_page":"7346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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/T10860","display_name":"Speech 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":0.8163617849349976},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7387198805809021},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6684523820877075},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6613748073577881},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6347582340240479},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5290324091911316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5231884121894836},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4935523271560669},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4570775628089905},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42158833146095276},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41755279898643494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32645153999328613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163617849349976},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7387198805809021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6684523820877075},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6613748073577881},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6347582340240479},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5290324091911316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231884121894836},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4935523271560669},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4570775628089905},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42158833146095276},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41755279898643494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32645153999328613},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"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:10.1109/icassp43922.2022.9747460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747460","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":37,"referenced_works":["https://openalex.org/W105569935","https://openalex.org/W1494198834","https://openalex.org/W1882958252","https://openalex.org/W2146334809","https://openalex.org/W2399733683","https://openalex.org/W2625297138","https://openalex.org/W2726515241","https://openalex.org/W2803193013","https://openalex.org/W2842511635","https://openalex.org/W2885005742","https://openalex.org/W2889374687","https://openalex.org/W2962770129","https://openalex.org/W2963467407","https://openalex.org/W2972602947","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973181312","https://openalex.org/W2982223350","https://openalex.org/W3015267357","https://openalex.org/W3015734344","https://openalex.org/W3016181583","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3095334805","https://openalex.org/W3095789936","https://openalex.org/W3097286738","https://openalex.org/W3197580070","https://openalex.org/W3197642003","https://openalex.org/W3198668286","https://openalex.org/W3198858531","https://openalex.org/W3209059054","https://openalex.org/W4297808394","https://openalex.org/W6639480849","https://openalex.org/W6773803412","https://openalex.org/W6780218876","https://openalex.org/W6780361010","https://openalex.org/W6784776607"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3006475563","https://openalex.org/W2060789910","https://openalex.org/W3015707499","https://openalex.org/W2049462786","https://openalex.org/W4287868249","https://openalex.org/W2326728821","https://openalex.org/W4297798768","https://openalex.org/W1604435341","https://openalex.org/W3204853141"],"abstract_inverted_index":{"Large":[0],"speech":[1,55],"emotion":[2,56],"recognition":[3,57],"datasets":[4,11],"are":[5,19],"hard":[6],"to":[7,21,39],"obtain,":[8],"and":[9,25,77,80],"small":[10],"may":[12],"contain":[13],"biases.":[14],"Deep-net-based":[15],"classifiers,":[16],"in":[17],"turn,":[18],"prone":[20],"exploit":[22],"those":[23],"biases":[24],"find":[26],"shortcuts":[27,33],"such":[28],"as":[29],"speaker":[30,61],"characteristics.":[31],"These":[32],"usually":[34],"harm":[35],"a":[36,47,54],"model\u2019s":[37],"ability":[38],"generalize.":[40],"To":[41],"address":[42],"this":[43],"challenge,":[44],"we":[45],"propose":[46],"gradient-based":[48],"adversary":[49],"learning":[50],"framework":[51],"that":[52],"learns":[53],"task":[58],"while":[59],"normalizing":[60],"characteristics":[62],"from":[63],"the":[64,69,86],"feature":[65],"representation.":[66],"We":[67],"demonstrate":[68],"efficacy":[70],"of":[71],"our":[72],"method":[73],"on":[74,85],"both":[75],"speaker-independent":[76],"speaker-dependent":[78],"settings":[79],"obtain":[81],"new":[82],"state-of-the-art":[83],"results":[84],"challenging":[87],"IEMOCAP":[88],"dataset.":[89]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":7}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}