{"id":"https://openalex.org/W4319586925","doi":"https://doi.org/10.1109/iscslp57327.2022.10038178","title":"AdaptiveFormer: A Few-shot Speaker Adaptive Speech Synthesis Model based on FastSpeech2","display_name":"AdaptiveFormer: A Few-shot Speaker Adaptive Speech Synthesis Model based on FastSpeech2","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586925","doi":"https://doi.org/10.1109/iscslp57327.2022.10038178"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038178","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5102845007","display_name":"Dengfeng Ke","orcid":"https://orcid.org/0000-0001-8459-0412"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dengfeng Ke","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076551862","display_name":"Ruixin Hu","orcid":"https://orcid.org/0000-0002-0999-0712"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixin Hu","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057554364","display_name":"Qi Luo","orcid":"https://orcid.org/0009-0000-8290-5441"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Luo","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068030070","display_name":"Liangjie Huang","orcid":"https://orcid.org/0000-0003-0770-1582"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangjie Huang","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001927761","display_name":"Wenhan Yao","orcid":"https://orcid.org/0000-0003-1014-9565"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Yao","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005711805","display_name":"Wentao Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Shu","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052176517","display_name":"Jinsong Zhang","orcid":"https://orcid.org/0000-0002-1603-3136"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Zhang","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006684220","display_name":"Yanlu Xie","orcid":"https://orcid.org/0000-0001-6765-4808"},"institutions":[{"id":"https://openalex.org/I115212828","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36","country_code":"CN","type":"education","lineage":["https://openalex.org/I115212828"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlu Xie","raw_affiliation_strings":["Beijing Language and Culture University,Beijing,China","Beijing Language and Culture University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Language and Culture University,Beijing,China","institution_ids":["https://openalex.org/I115212828"]},{"raw_affiliation_string":"Beijing Language and Culture University, Beijing, China","institution_ids":["https://openalex.org/I115212828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102845007"],"corresponding_institution_ids":["https://openalex.org/I115212828"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20378151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"229"},"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/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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/T10028","display_name":"Topic Modeling","score":0.9909999966621399,"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":0.7932010889053345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6969434022903442},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6099861860275269},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4459739029407501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40351614356040955}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932010889053345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6969434022903442},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6099861860275269},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4459739029407501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40351614356040955},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038178","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320325046","display_name":"Beijing Language and Culture University","ror":"https://ror.org/03te2zs36"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2788357188","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2972574864","https://openalex.org/W2990138404","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3033411150","https://openalex.org/W3128910262","https://openalex.org/W3161296985","https://openalex.org/W3196584150","https://openalex.org/W3197294703","https://openalex.org/W3198533616","https://openalex.org/W3200756692","https://openalex.org/W3213544594","https://openalex.org/W4205742757","https://openalex.org/W4221156079","https://openalex.org/W4385245566","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6790220310","https://openalex.org/W6805710207"],"related_works":["https://openalex.org/W2063185616","https://openalex.org/W3107474891","https://openalex.org/W2794438528","https://openalex.org/W2159150199","https://openalex.org/W2143116775","https://openalex.org/W2464831953","https://openalex.org/W1498035869","https://openalex.org/W2162397380","https://openalex.org/W1976467904","https://openalex.org/W1997732994"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"adaptive":[3,29,60,92],"text-to-speech":[4],"(TTS)":[5],"has":[6],"attracted":[7],"increasing":[8],"interests":[9],"in":[10],"speech":[11,27,69],"community,":[12],"which":[13,66,120],"aims":[14],"at":[15],"synthesizing":[16],"a":[17,58,90,106,122],"new":[18,59],"speaker\u2019s":[19],"voice":[20],"with":[21,49,70],"few":[22],"data.":[23,51],"However,":[24],"the":[25,35,82,97,111,130,137,145,153,158,162,169],"synthesized":[26,85],"of":[28,37,84,139],"TTS":[30,61],"model":[31,160],"is":[32,42,121],"still":[33],"facing":[34],"challenge":[36],"performance":[38],"degradation,":[39],"because":[40],"it":[41],"difficult":[43],"to":[44,80,95,109,135,152],"learn":[45],"unseen":[46,74,149,170],"speaker":[47,146],"style":[48],"limited":[50],"To":[52],"tackle":[53],"this":[54],"problem,":[55],"we":[56],"propose":[57,89,105],"model,":[62],"called":[63],"AdaptiveFormer":[64],"(AF),":[65],"generates":[67],"natural":[68],"high":[71],"similarity":[72],"for":[73,148],"speaker.":[75,150],"We":[76,88,104,128],"use":[77,129],"two":[78],"methods":[79],"improve":[81,144],"quality":[83],"speech.":[86],"1)":[87],"novel":[91],"attention":[93,101],"mechanism":[94],"replace":[96],"traditional":[98],"multi-head":[99],"self":[100],"mechanism.":[102],"2)":[103],"Conditional":[107,131],"Predictor":[108],"predict":[110],"valuable":[112],"rhythm":[113,141],"information,":[114,142],"including":[115],"duration,":[116],"pitch":[117],"and":[118,143,155],"energy,":[119],"Variance":[123],"Adaptor":[124],"[1]":[125,166],"based":[126],"architecture.":[127],"Layer":[132],"Normalization":[133],"(CLN)":[134],"enhance":[136],"accuracy":[138],"predicted":[140],"adaptation":[147],"According":[151],"MOS":[154],"SMOS":[156],"results,":[157],"AF":[159],"outperforms":[161],"baseline":[163],"(spk":[164],"emb)":[165],"approach":[167],"on":[168],"emotional":[171],"corpus.":[172]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}