{"id":"https://openalex.org/W4393147249","doi":"https://doi.org/10.1609/aaai.v38i16.29793","title":"Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations","display_name":"Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W4393147249","doi":"https://doi.org/10.1609/aaai.v38i16.29793"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v38i16.29793","doi":"https://doi.org/10.1609/aaai.v38i16.29793","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i16.29793","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29793/31372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29793/31372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101455200","display_name":"Yejin Jeon","orcid":"https://orcid.org/0000-0002-0077-9232","observed_orcids":["https://orcid.org/0000-0002-0077-9232"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yejin Jeon","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090577558","display_name":"Yunsu Kim","orcid":"https://orcid.org/0009-0005-2948-4306","observed_orcids":["https://orcid.org/0009-0005-2948-4306"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunsu Kim","raw_affiliation_strings":["aiXplain, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"aiXplain, Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045508648","display_name":"Gary Geunbae Lee","orcid":"https://orcid.org/0000-0002-3692-6732","observed_orcids":["https://orcid.org/0000-0002-3692-6732","https://orcid.org/0000-0003-4788-0140"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gary Geunbae Lee","raw_affiliation_strings":["POSTECH"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"POSTECH","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4736,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6255787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"38","issue":"16","first_page":"18336","last_page":"18344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":9.999999747378752e-05,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/content-leakage","display_name":"content leakage","score":0.7850000262260437},{"id":"https://openalex.org/keywords/speaker-disentanglement","display_name":"speaker disentanglement","score":0.9700000286102295},{"id":"https://openalex.org/keywords/attention-pooling","display_name":"attention pooling","score":0.8289999961853027},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.5249999761581421}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.7222533226013184},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6337437033653259},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5622044205665588},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5283458828926086},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5052669644355774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39432668685913086},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.32761937379837036},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2883721888065338},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2283424735069275},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07468757033348083},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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":4,"locations":[{"id":"doi:10.1609/aaai.v38i16.29793","doi":"https://doi.org/10.1609/aaai.v38i16.29793","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i16.29793","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29793/31372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2401.02014","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.02014","pdf_url":"https://arxiv.org/pdf/2401.02014","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/29793","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/29793","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2401.02014","doi":"https://doi.org/10.48550/arxiv.2401.02014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.02014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v38i16.29793","doi":"https://doi.org/10.1609/aaai.v38i16.29793","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1609/aaai.v38i16.29793","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/29793/31372","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1903519916","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G2702555917","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2763392412","display_name":null,"funder_award_id":"R2021040136","funder_id":"https://openalex.org/F4320323890","funder_display_name":"Korea Creative Content Agency"},{"id":"https://openalex.org/G6946461118","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320321282","funder_display_name":"Pohang University of Science and Technology"},{"id":"https://openalex.org/G705716709","display_name":null,"funder_award_id":"No.2019-0-01906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320321282","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12"},{"id":"https://openalex.org/F4320322006","display_name":"Ministry of Culture, Sports and Tourism","ror":"https://ror.org/02fkk6k65"},{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393147249.pdf","grobid_xml":"https://content.openalex.org/works/W4393147249.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W142801778","https://openalex.org/W2120847449","https://openalex.org/W2475287302","https://openalex.org/W2532494225","https://openalex.org/W2545656684","https://openalex.org/W2572730214","https://openalex.org/W2593463961","https://openalex.org/W2603777577","https://openalex.org/W2626778328","https://openalex.org/W2786672974","https://openalex.org/W2789758093","https://openalex.org/W2892620417","https://openalex.org/W2902070858","https://openalex.org/W2946555236","https://openalex.org/W2949973225","https://openalex.org/W2963432880","https://openalex.org/W2963539064","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W2981934523","https://openalex.org/W3007067948","https://openalex.org/W3015212100","https://openalex.org/W3033411150","https://openalex.org/W3036601975","https://openalex.org/W3098403858","https://openalex.org/W3128910262","https://openalex.org/W3161838540","https://openalex.org/W3168527213","https://openalex.org/W3179803166","https://openalex.org/W3185372235","https://openalex.org/W3185823442","https://openalex.org/W3205631867","https://openalex.org/W4210777104","https://openalex.org/W4221156079","https://openalex.org/W4286782564","https://openalex.org/W4286905904","https://openalex.org/W4307323391","https://openalex.org/W4311000453","https://openalex.org/W4319781852","https://openalex.org/W4372259784"],"related_works":["https://openalex.org/W4389286232","https://openalex.org/W4226050434","https://openalex.org/W4221156079","https://openalex.org/W3158102353","https://openalex.org/W7044505557","https://openalex.org/W4224917388","https://openalex.org/W4403007528","https://openalex.org/W4200631896","https://openalex.org/W2982277844","https://openalex.org/W4312095868"],"abstract_inverted_index":{"Zero-shot":[0],"multi-speaker":[1],"TTS":[2],"aims":[3],"to":[4,25,33,97,119,142,156,171],"synthesize":[5],"speech":[6],"with":[7,164],"the":[8,60,66,75,99,128,140,148,159,165,175,185],"voice":[9],"of":[10,28,101,139,174,187],"a":[11,115],"chosen":[12],"target":[13,144,166],"speaker":[14,35,55,76,93,103,130,162],"without":[15],"any":[16],"fine-tuning.":[17],"Prevailing":[18],"methods,":[19],"however,":[20],"encounter":[21],"limitations":[22],"at":[23],"adapting":[24],"new":[26],"speakers":[27],"out-of-domain":[29],"settings,":[30],"primarily":[31],"due":[32],"inadequate":[34],"disentanglement":[36],"and":[37,113,126,177,182,193],"content":[38,72,84],"leakage.":[39],"To":[40,122],"overcome":[41],"these":[42,124],"constraints,":[43],"we":[44,105,132,151],"propose":[45],"an":[46],"innovative":[47],"negation":[48,79],"feature":[49],"learning":[50,100],"paradigm":[51,117],"that":[52],"models":[53],"decoupled":[54],"attributes":[56,196],"as":[57,169],"deviations":[58],"from":[59,74],"complete":[61],"audio":[62,178],"representation":[63,163],"by":[64],"utilizing":[65],"subtraction":[67],"operation.":[68],"By":[69],"eliminating":[70],"superfluous":[71],"information":[73],"representation,":[77,131],"our":[78,188],"scheme":[80],"not":[81],"only":[82],"mitigates":[83],"leakage,":[85],"thereby":[86],"enhancing":[87],"synthesis":[88],"robustness,":[89],"but":[90],"also":[91],"improves":[92],"fidelity.":[94],"In":[95],"addition,":[96],"facilitate":[98],"diverse":[102],"attributes,":[104],"leverage":[106],"multi-stream":[107],"Transformers,":[108],"which":[109],"retain":[110],"multiple":[111],"hypotheses":[112,125],"instigate":[114],"training":[116],"akin":[118],"ensemble":[120],"learning.":[121],"unify":[123],"realize":[127],"final":[129],"employ":[133],"attention":[134],"pooling.":[135],"Finally,":[136],"in":[137,147,191],"light":[138],"imperative":[141],"generate":[143],"text":[145,167,176],"utterances":[146],"desired":[149],"voice,":[150],"adopt":[152],"adaptive":[153],"layer":[154],"normalizations":[155],"effectively":[157],"fuse":[158],"previously":[160],"generated":[161],"representations,":[168],"opposed":[170],"mere":[172],"concatenation":[173],"modalities.":[179],"Extensive":[180],"experiments":[181],"validations":[183],"substantiate":[184],"efficacy":[186],"proposed":[189],"approach":[190],"preserving":[192],"harnessing":[194],"speaker-specific":[195],"vis-\u00e0-vis":[197],"alternative":[198],"baseline":[199],"models.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-03-26T00:00:00"}