{"id":"https://openalex.org/W4392909765","doi":"https://doi.org/10.1109/icassp48485.2024.10446186","title":"Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer","display_name":"Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909765","doi":"https://doi.org/10.1109/icassp48485.2024.10446186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5023714181","display_name":"Leyuan Qu","orcid":"https://orcid.org/0000-0001-6694-5355"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Leyuan Qu","raw_affiliation_strings":["Zhejiang Lab,China","Zhejiang Lab, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391928","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-2990-229X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Xinjiang University,China","Xinjiang University, China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025003","display_name":"Cornelius Weber","orcid":"https://orcid.org/0000-0001-5163-938X"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Weber","raw_affiliation_strings":["University of Hamburg,Germany","University of Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003467187","display_name":"Pengcheng Yue","orcid":"https://orcid.org/0000-0001-6210-169X"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Yue","raw_affiliation_strings":["Zhejiang Lab,China","Zhejiang Lab, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021697903","display_name":"Taihao Li","orcid":"https://orcid.org/0000-0003-3279-7125"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taihao Li","raw_affiliation_strings":["Zhejiang Lab,China","Zhejiang Lab, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang Lab,China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Lab, China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["University of Hamburg,Germany","University of Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023714181"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":1.6462,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82946476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10101","last_page":"10105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.919700026512146,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.919700026512146,"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/speech-recognition","display_name":"Speech recognition","score":0.7167180180549622},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6713520884513855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6674826145172119},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6196990013122559},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42818179726600647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3558393716812134},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07872843742370605}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7167180180549622},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6713520884513855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6674826145172119},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6196990013122559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42818179726600647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3558393716812134},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07872843742370605},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307500","display_name":"Youth Foundation","ror":null},{"id":"https://openalex.org/F4320325419","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W2146334809","https://openalex.org/W2407080277","https://openalex.org/W2891205112","https://openalex.org/W2936774411","https://openalex.org/W2951442257","https://openalex.org/W2963914279","https://openalex.org/W2964243274","https://openalex.org/W2972498864","https://openalex.org/W2972724712","https://openalex.org/W3015241559","https://openalex.org/W3024869864","https://openalex.org/W3025680351","https://openalex.org/W3092028330","https://openalex.org/W3126625480","https://openalex.org/W3162475537","https://openalex.org/W3162890625","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221162872","https://openalex.org/W4254718357","https://openalex.org/W4361994820","https://openalex.org/W6623517193","https://openalex.org/W6675409298","https://openalex.org/W6750489868","https://openalex.org/W6783867762","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W3204019825","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Humans":[0],"can":[1,148,200],"effortlessly":[2],"modify":[3],"various":[4],"prosodic":[5,103],"attributes,":[6,104],"such":[7,105],"as":[8,106,137],"the":[9,14,47,82,116,133,142,156,176,182],"placement":[10],"of":[11,16,58,98,126],"stress":[12],"and":[13,45,62,69,109,159,173,185],"intensity":[15],"sentiment,":[17],"to":[18,41,122,131],"convey":[19],"a":[20,35,59,63,74,165],"specific":[21],"emotion":[22,53],"while":[23,154],"maintaining":[24],"consistent":[25],"linguistic":[26],"content.":[27,161],"Motivated":[28],"by":[29,79,111,171,194],"this":[30],"capability,":[31],"we":[32,163],"propose":[33],"EmoAug,":[34],"novel":[36],"style":[37],"transfer":[38,150],"model":[39,167,178],"designed":[40],"enhance":[42],"emotional":[43,99],"expression":[44],"tackle":[46,132],"data":[48,134,169,195],"scarcity":[49],"issue":[50,136],"in":[51,87],"speech":[52,77,100],"recognition":[54],"tasks.":[55],"EmoAug":[56,95,119,147,172],"consists":[57],"semantic":[60,160],"encoder":[61,65],"paralinguistic":[64,117],"that":[66,146,175],"represent":[67],"verbal":[68],"non-verbal":[70],"information":[71,85],"respectively.":[72],"Additionally,":[73],"decoder":[75],"reconstructs":[76],"signals":[78],"conditioning":[80],"on":[81,141,203],"aforementioned":[83],"two":[84],"flows":[86],"an":[88],"unsupervised":[89],"fashion.":[90],"Once":[91],"training":[92],"is":[93],"completed,":[94],"enriches":[96],"expressions":[97],"with":[101,168],"different":[102,113,151],"stress,":[107],"rhythm":[108],"intensity,":[110],"feeding":[112],"styles":[114,153],"into":[115],"encoder.":[118],"enables":[120],"us":[121],"generate":[123],"similar":[124],"numbers":[125],"samples":[127,199],"for":[128],"each":[129],"class":[130],"imbalance":[135],"well.":[138],"Experimental":[139],"results":[140],"IEMOCAP":[143],"dataset":[144],"demonstrate":[145],"successfully":[149],"speaking":[152],"retaining":[155],"speaker":[157],"identity":[158],"Furthermore,":[162],"train":[164],"SER":[166],"augmented":[170,177],"show":[174],"not":[179],"only":[180],"surpasses":[181],"state-of-the-art":[183],"supervised":[184],"self-supervised":[186],"methods":[187],"but":[188],"also":[189],"overcomes":[190],"overfitting":[191],"problems":[192],"caused":[193],"imbalance.":[196],"Some":[197],"audio":[198],"be":[201],"found":[202],"our":[204],"demo":[205],"website":[206],"<sup":[207],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[208],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[209],".":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}