{"id":"https://openalex.org/W3211358952","doi":"https://doi.org/10.1109/taslp.2021.3125142","title":"Language Agnostic Speaker Embedding for Cross-Lingual Personalized Speech Generation","display_name":"Language Agnostic Speaker Embedding for Cross-Lingual Personalized Speech Generation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3211358952","doi":"https://doi.org/10.1109/taslp.2021.3125142","mag":"3211358952"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3125142","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125142","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/taslp.2021.3125142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101846956","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-8520-8227"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Electrical and Computer Engineering, National University of Singapore, 37580 Singapore, Singapore, 117583 (e-mail: E0154158@u.nus.edu)"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, National University of Singapore, 37580 Singapore, Singapore, 117583 (e-mail: E0154158@u.nus.edu)","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156833","display_name":"Xiaohai Tian","orcid":"https://orcid.org/0000-0001-5219-1249"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":["Electrical and Computer Engineering, National University of Singapore, 37580 Singapore, Singapore, Singapore, 119077 (e-mail: eletia@nus.edu.sg)","[Speech and Audio Department, Bytedance AI Lab., Singapore, Singapore]"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, National University of Singapore, 37580 Singapore, Singapore, Singapore, 119077 (e-mail: eletia@nus.edu.sg)","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"[Speech and Audio Department, Bytedance AI Lab., Singapore, Singapore]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore, (e-mail: haizhou.li@nus.edu.sg)"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore, (e-mail: haizhou.li@nus.edu.sg)","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101846956"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.9598,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88792673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"3427","last_page":"3439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","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":0.8259585499763489},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941968202590942},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6780996322631836},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5264968276023865},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4786756634712219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4643924832344055},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4551733136177063},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4489263892173767},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.418700635433197},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4084942936897278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21407175064086914},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06937998533248901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259585499763489},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941968202590942},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6780996322631836},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5264968276023865},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4786756634712219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4643924832344055},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4551733136177063},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4489263892173767},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.418700635433197},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4084942936897278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21407175064086914},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06937998533248901},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3125142","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125142","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/233329","is_oa":true,"landing_page_url":"https://scholarbank.nus.edu.sg/handle/10635/233329","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus OA2021","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3125142","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3125142","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3191157935","display_name":null,"funder_award_id":"AISG-100E-2018-006","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320334971","display_name":"Science and Engineering Research Council","ror":"https://ror.org/00zgdb249"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":111,"referenced_works":["https://openalex.org/W799143314","https://openalex.org/W854541894","https://openalex.org/W1499332833","https://openalex.org/W1509691205","https://openalex.org/W1524333225","https://openalex.org/W1561695604","https://openalex.org/W1571950845","https://openalex.org/W1600722501","https://openalex.org/W1836465849","https://openalex.org/W1990505856","https://openalex.org/W2043273367","https://openalex.org/W2046056978","https://openalex.org/W2079623482","https://openalex.org/W2086796102","https://openalex.org/W2115638247","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2134973740","https://openalex.org/W2149270762","https://openalex.org/W2150659647","https://openalex.org/W2150769028","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2187089797","https://openalex.org/W2188791853","https://openalex.org/W2294351487","https://openalex.org/W2400063444","https://openalex.org/W2405774341","https://openalex.org/W2462831000","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2610836895","https://openalex.org/W2615413256","https://openalex.org/W2758785877","https://openalex.org/W2795109282","https://openalex.org/W2804998325","https://openalex.org/W2806000759","https://openalex.org/W2808706139","https://openalex.org/W2889048668","https://openalex.org/W2889061305","https://openalex.org/W2889064624","https://openalex.org/W2890964092","https://openalex.org/W2892734764","https://openalex.org/W2897353073","https://openalex.org/W2904459034","https://openalex.org/W2907262790","https://openalex.org/W2913340405","https://openalex.org/W2936780106","https://openalex.org/W2938583109","https://openalex.org/W2945478979","https://openalex.org/W2946555236","https://openalex.org/W2952161038","https://openalex.org/W2962788625","https://openalex.org/W2962896155","https://openalex.org/W2962993426","https://openalex.org/W2963035245","https://openalex.org/W2963252329","https://openalex.org/W2963542120","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W2972369255","https://openalex.org/W2972544500","https://openalex.org/W2972921407","https://openalex.org/W2979593053","https://openalex.org/W3007502375","https://openalex.org/W3011193554","https://openalex.org/W3015338123","https://openalex.org/W3015826515","https://openalex.org/W3042801391","https://openalex.org/W3043140951","https://openalex.org/W3082130377","https://openalex.org/W3092246895","https://openalex.org/W3095862185","https://openalex.org/W3096514088","https://openalex.org/W3099078140","https://openalex.org/W3102628737","https://openalex.org/W3132762163","https://openalex.org/W3133917823","https://openalex.org/W3154451338","https://openalex.org/W3168542456","https://openalex.org/W3197991492","https://openalex.org/W3198791321","https://openalex.org/W4245885054","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6633526003","https://openalex.org/W6634201745","https://openalex.org/W6638667902","https://openalex.org/W6682344342","https://openalex.org/W6682365201","https://openalex.org/W6687054766","https://openalex.org/W6712610176","https://openalex.org/W6718683173","https://openalex.org/W6720742747","https://openalex.org/W6738465933","https://openalex.org/W6745117592","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6754473786","https://openalex.org/W6762533536","https://openalex.org/W6764882207","https://openalex.org/W6784756737","https://openalex.org/W6791578994","https://openalex.org/W6801259823","https://openalex.org/W6840412704","https://openalex.org/W6936113694","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Cross-lingual":[0],"personalized":[1,61,139],"speech":[2,30,62,119,140],"generation":[3,141],"seeks":[4],"to":[5,27,81,91],"synthesize":[6],"a":[7,13,20,29,33,43,69,76],"target":[8,39],"speakers":[9],"voice":[10,107],"from":[11,96],"only":[12],"few":[14],"training":[15],"samples":[16],"that":[17,36,74,116,128],"are":[18],"in":[19,59,142],"different":[21],"language.":[22],"One":[23],"popular":[24],"technique":[25],"is":[26,46,133],"condition":[28],"synthesizer":[31],"on":[32,105],"speaker":[34,44,57,71,79,83,97,131,145],"embedding,":[35],"characterizes":[37],"the":[38,50,56,93,129],"speaker.":[40],"Unfortunately,":[41],"such":[42],"embedding":[45,80,132],"usually":[47],"affected":[48],"by":[49],"language":[51,77,94,134],"being":[52],"spoken,":[53],"which":[54],"compromises":[55],"similarity":[58],"cross-lingual":[60,118,138],"generation.":[63,120],"In":[64],"this":[65],"paper,":[66],"we":[67,86],"propose":[68],"novel":[70],"encoding":[72],"mechanism":[73],"learns":[75],"agnostic":[78],"characterize":[82],"individuality.":[84],"Specifically,":[85],"adopt":[87],"an":[88],"encoder-decoder":[89],"architecture":[90],"disentangle":[92],"information":[95],"embeddings":[98],"via":[99],"multi-task":[100],"learning.":[101],"We":[102],"conduct":[103],"experiments":[104],"both":[106],"conversion":[108],"and":[109,114,123],"text-to-speech":[110],"synthesis":[111],"between":[112],"English":[113],"Mandarin":[115],"involve":[117],"All":[121],"objective":[122],"subjective":[124],"evaluations":[125],"consistently":[126],"confirm":[127],"proposed":[130],"agnostic,":[135],"thus":[136],"improving":[137],"terms":[143],"of":[144],"similarity.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}