{"id":"https://openalex.org/W3206831804","doi":"https://doi.org/10.1109/icassp43922.2022.9746968","title":"Towards Lifelong Learning of Multilingual Text-to-Speech Synthesis","display_name":"Towards Lifelong Learning of Multilingual Text-to-Speech Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206831804","doi":"https://doi.org/10.1109/icassp43922.2022.9746968","mag":"3206831804"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746968","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/A5112695849","display_name":"Mu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mu Yang","raw_affiliation_strings":["University of Texas at Dallas,Richardson,Texas,USA","University of Texas at Dallas, Richardson, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas,Richardson,Texas,USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"University of Texas at Dallas, Richardson, Texas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaojin Ding","raw_affiliation_strings":["Texas A&M University,College Station,Texas,USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University,College Station,Texas,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034062241","display_name":"Tianlong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianlong Chen","raw_affiliation_strings":["University of Texas at Austin,Austin,Texas,USA","University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Austin,Texas,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450967","display_name":"Tong Wang","orcid":"https://orcid.org/0000-0001-6981-916X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048522863","display_name":"Zhangyang Wang","orcid":"https://orcid.org/0000-0002-2050-5693"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhangyang Wang","raw_affiliation_strings":["University of Texas at Austin,Austin,Texas,USA","University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Austin,Texas,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5112695849"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.3122,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.46732748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"8022","last_page":"8026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996999979019165,"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/lifelong-learning","display_name":"Lifelong learning","score":0.8173936605453491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8124030828475952},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7353310585021973},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801515579223633},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5324341654777527},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48658740520477295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4715431034564972},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42089757323265076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3948875963687897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32344353199005127}],"concepts":[{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.8173936605453491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8124030828475952},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7353310585021973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801515579223633},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5324341654777527},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48658740520477295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4715431034564972},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42089757323265076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3948875963687897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32344353199005127},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746968","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2107860279","https://openalex.org/W2400517318","https://openalex.org/W2426267443","https://openalex.org/W2473930607","https://openalex.org/W2554616628","https://openalex.org/W2560647685","https://openalex.org/W2734314755","https://openalex.org/W2806984819","https://openalex.org/W2901389167","https://openalex.org/W2952571470","https://openalex.org/W2957543415","https://openalex.org/W2962724315","https://openalex.org/W2962933664","https://openalex.org/W2964088867","https://openalex.org/W2964189064","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972473628","https://openalex.org/W2972802841","https://openalex.org/W2973034126","https://openalex.org/W2981864462","https://openalex.org/W3011401432","https://openalex.org/W3030364939","https://openalex.org/W3091787298","https://openalex.org/W3095012670","https://openalex.org/W3097297926","https://openalex.org/W3097968133","https://openalex.org/W3123155632","https://openalex.org/W3126996274","https://openalex.org/W3138136049","https://openalex.org/W3144613143","https://openalex.org/W3156192236","https://openalex.org/W3181257032","https://openalex.org/W3186596101","https://openalex.org/W3196671011","https://openalex.org/W3198094329","https://openalex.org/W4287253086","https://openalex.org/W4295883599","https://openalex.org/W4298580827","https://openalex.org/W4319988532","https://openalex.org/W6730146409","https://openalex.org/W6748409065","https://openalex.org/W6751907932","https://openalex.org/W6757094361","https://openalex.org/W6774893473","https://openalex.org/W6788757688","https://openalex.org/W6790414116","https://openalex.org/W6792462441","https://openalex.org/W6798575157","https://openalex.org/W6799245484","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4248896073","https://openalex.org/W2974871044"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,9,74,82,93,99,139],"lifelong":[4,52,84,129],"learning":[5,53,85,95,122,130],"approach":[6,78],"to":[7,73,105,138],"train":[8],"multilingual":[10],"Text-To-Speech":[11],"(TTS)":[12],"system,":[13],"where":[14],"each":[15],"language":[16],"was":[17,24],"seen":[18],"as":[19,92],"an":[20],"individual":[21],"task":[22],"and":[23,27,39,44,97,114,127],"learned":[25],"sequentially":[26],"continually.":[28],"It":[29],"does":[30],"not":[31],"require":[32],"pooled":[33],"data":[34],"from":[35],"all":[36],"languages":[37,70],"altogether,":[38],"thus":[40],"alleviates":[41],"the":[42,49,89,107],"storage":[43],"computation":[45],"burden.":[46],"One":[47],"of":[48,51],"challenges":[50],"methods":[54],"is":[55],"\"catastrophic":[56],"forgetting\":":[57],"in":[58],"TTS":[59],"scenario":[60],"it":[61],"means":[62],"that":[63,119],"model":[64],"performance":[65],"quickly":[66],"degrades":[67],"on":[68],"previous":[69],"when":[71],"adapted":[72],"new":[75],"language.":[76],"We":[77,87],"this":[79,120],"problem":[80],"via":[81],"data-replay-based":[83],"method.":[86],"formulate":[88],"replay":[90],"process":[91],"supervised":[94,121],"problem,":[96],"propose":[98],"simple":[100],"yet":[101],"effective":[102],"dual-sampler":[103],"framework":[104],"tackle":[106],"heavily":[108],"language-imbalanced":[109],"training":[110],"samples.":[111],"Through":[112],"objective":[113],"subjective":[115],"evaluations,":[116],"we":[117],"show":[118],"formulation":[123],"outperforms":[124],"other":[125],"gradient-based":[126],"regularization-based":[128],"methods,":[131],"achieving":[132],"43%":[133],"Mel-Cepstral":[134],"Distortion":[135],"reduction":[136],"compared":[137],"fine-tuning":[140],"baseline.":[141]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}