{"id":"https://openalex.org/W4225304461","doi":"https://doi.org/10.1109/icassp43922.2022.9747239","title":"Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module","display_name":"Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225304461","doi":"https://doi.org/10.1109/icassp43922.2022.9747239"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747239","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/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adam Gabrys","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058343897","display_name":"Goeric Huybrechts","orcid":"https://orcid.org/0000-0003-0222-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goeric Huybrechts","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ming Chien","raw_affiliation_strings":["National Taiwan University (NTU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University (NTU)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053794772","display_name":"Julian Roth","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Roth","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041378836","display_name":"Giulia Comini","orcid":"https://orcid.org/0000-0002-9391-6565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giulia Comini","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033936072","display_name":"Bartek Perz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bartek Perz","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alexa AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5031116817"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9744,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88239347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7902","last_page":"7906"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9958999752998352,"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/T12031","display_name":"Speech and dialogue systems","score":0.9879000186920166,"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":0.7845393419265747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7619277238845825},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7219800353050232},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6288173198699951},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6008202433586121},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.594124972820282},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.5206412672996521},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47404953837394714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845393419265747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7619277238845825},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7219800353050232},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6288173198699951},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6008202433586121},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.594124972820282},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5206412672996521},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47404953837394714},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747239","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":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2288817436","https://openalex.org/W2752796333","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2889028433","https://openalex.org/W2892620417","https://openalex.org/W2933138175","https://openalex.org/W2962788625","https://openalex.org/W2963542120","https://openalex.org/W2963799213","https://openalex.org/W2971074500","https://openalex.org/W2972574864","https://openalex.org/W2973034126","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W3016159759","https://openalex.org/W3022876224","https://openalex.org/W3024747869","https://openalex.org/W3036601975","https://openalex.org/W3081416955","https://openalex.org/W3095035471","https://openalex.org/W3095199334","https://openalex.org/W3096086473","https://openalex.org/W3096303254","https://openalex.org/W3096524539","https://openalex.org/W3097531247","https://openalex.org/W3128910262","https://openalex.org/W3161492781","https://openalex.org/W3162794600","https://openalex.org/W3172021299","https://openalex.org/W3195171908","https://openalex.org/W4294619240","https://openalex.org/W4298857617","https://openalex.org/W6639824700","https://openalex.org/W6745569068","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6762931180","https://openalex.org/W6777445600","https://openalex.org/W6780218876","https://openalex.org/W6790220310","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W1540615732","https://openalex.org/W2405110677","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W642007152","https://openalex.org/W596245619","https://openalex.org/W2184127972","https://openalex.org/W168921769","https://openalex.org/W2899676847","https://openalex.org/W2320148263"],"abstract_inverted_index":{"State-of-the-art":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3,37],"require":[4],"several":[5],"hours":[6],"of":[7,20,60,135,143,149],"recorded":[8],"speech":[9,28,61,114,130,144],"data":[10],"to":[11,76,104,110,116],"generate":[12],"high-quality":[13,79],"synthetic":[14],"speech.":[15],"When":[16],"using":[17],"reduced":[18],"amounts":[19],"training":[21,34],"data,":[22],"standard":[23],"TTS":[24,36,48,80,90,95,108,156],"models":[25],"suffer":[26],"from":[27,62],"quality":[29],"and":[30,82,137],"intelligibility":[31],"degradations,":[32],"making":[33],"low-resource":[35,47],"problematic.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,102],"propose":[43,103],"a":[44,63,72,77,84,98,106,112,146,155],"novel":[45],"extremely":[46],"method":[49],"called":[50],"Voice":[51,125],"Filter":[52,126],"that":[53,123],"uses":[54,67],"as":[55,57,71,97],"little":[56],"one":[58,141],"minute":[59,142],"target":[64],"speaker.":[65],"It":[66],"voice":[68],"conversion":[69],"(VC)":[70],"post-processing":[73],"module":[74],"appended":[75],"pre-existing":[78],"system":[81,109],"marks":[83],"conceptual":[85],"shift":[86],"in":[87,133],"the":[88,93,118,124],"existing":[89],"paradigm,":[91],"framing":[92],"few-shot":[94,129],"problem":[96],"VC":[99,119],"task.":[100,120],"Furthermore,":[101],"use":[105],"duration-controllable":[107],"create":[111],"parallel":[113],"corpus":[115],"facilitate":[117],"Results":[121],"show":[122],"outperforms":[127],"state-of-the-art":[128],"synthesis":[131],"techniques":[132],"terms":[134],"objective":[136],"subjective":[138],"metrics":[139],"on":[140,145,159],"diverse":[147],"set":[148],"voices,":[150],"while":[151],"being":[152],"competitive":[153],"against":[154],"model":[157],"built":[158],"30":[160],"times":[161],"more":[162],"data.":[163],"<sup":[164],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-13T08:25:38.343686","created_date":"2025-10-10T00:00:00"}