{"id":"https://openalex.org/W4297841931","doi":"https://doi.org/10.21437/interspeech.2022-288","title":"AdaVocoder: Adaptive Vocoder for Custom Voice","display_name":"AdaVocoder: Adaptive Vocoder for Custom Voice","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841931","doi":"https://doi.org/10.21437/interspeech.2022-288"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-288","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-288","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100650415","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0002-1298-4399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":["VXI, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VXI, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062471070","display_name":"Robin Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robin Feng","raw_affiliation_strings":["VXI, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VXI, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028881152","display_name":"Mingming Ye","orcid":"https://orcid.org/0000-0002-5959-6780"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingming Ye","raw_affiliation_strings":["VXI, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VXI, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003066624","display_name":"Cheng Tuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Tuo","raw_affiliation_strings":["VXI, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VXI, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059932348","display_name":"Minhang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minhang Zhang","raw_affiliation_strings":["VXI, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VXI, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1687,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42260053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1586","last_page":"1590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9916999936103821,"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":0.9797999858856201,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8721131086349487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7296960353851318},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7136409282684326},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5252246856689453},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47805503010749817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3018624782562256},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22685489058494568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721131086349487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7296960353851318},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7136409282684326},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5252246856689453},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47805503010749817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3018624782562256},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22685489058494568},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-288","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-288","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1882958252","https://openalex.org/W2519091744","https://openalex.org/W2601450892","https://openalex.org/W2604763608","https://openalex.org/W2786808285","https://openalex.org/W2788357188","https://openalex.org/W2890983311","https://openalex.org/W2892620417","https://openalex.org/W2954386831","https://openalex.org/W2962964479","https://openalex.org/W2963341924","https://openalex.org/W2963675401","https://openalex.org/W2964243274","https://openalex.org/W2964268978","https://openalex.org/W2970006822","https://openalex.org/W2972574864","https://openalex.org/W2994373303","https://openalex.org/W3015338123","https://openalex.org/W3016159759","https://openalex.org/W3024747869","https://openalex.org/W3033411150","https://openalex.org/W3047334337","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3103104054","https://openalex.org/W3128910262","https://openalex.org/W3161109662","https://openalex.org/W3174480022","https://openalex.org/W3174758275","https://openalex.org/W3178839419","https://openalex.org/W3197294703","https://openalex.org/W4294646197","https://openalex.org/W4297817572","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4387297750","https://openalex.org/W127416991"],"abstract_inverted_index":{"Custom":[0],"voice":[1,31,101,174],"is":[2,32,76],"to":[3,17,27,33,106,119],"construct":[4,137],"a":[5,29,40,44,49,73,84,115,171,181,186],"personal":[6],"speech":[7,14],"synthesis":[8,15],"system":[9,175],"by":[10,125,179],"adapting":[11],"the":[12,18,22,63,79,87,90,108,121,126,131,146,159],"source":[13,147],"model":[16,20,38,149,184],"target":[19,23,91],"through":[21],"few":[24,164],"recordings.The":[25],"solution":[26],"constructing":[28],"custom":[30,100,173],"combine":[34],"an":[35,96],"adaptive":[36,97,111,139,182,187],"acoustic":[37,183],"with":[39,86,163,185],"robust":[41,45],"vocoder.However,":[42],"training":[43],"vocoder":[46,65,98,112,129,148],"usually":[47],"requires":[48],"multi-speaker":[50,74],"dataset,":[51],"which":[52],"should":[53],"include":[54],"various":[55,59],"age":[56],"groups":[57],"and":[58,78,142,152],"timbres,":[60],"so":[61],"that":[62,170],"trained":[64],"can":[66,176],"be":[67,177],"used":[68],"for":[69,99],"unseen":[70],"speakers.Collecting":[71],"such":[72],"dataset":[75,80,161],"difficult,":[77],"distribution":[81,88],"always":[82],"has":[83],"mismatch":[85],"of":[89,134],"speaker":[92],"dataset.This":[93],"paper":[94],"proposes":[95],"from":[102],"another":[103],"novel":[104],"perspective":[105],"solve":[107,120],"above":[109],"problems.The":[110],"mainly":[113],"uses":[114],"cross-domain":[116],"consistency":[117],"loss":[118],"overfitting":[122],"problem":[123],"encountered":[124],"GAN-based":[127],"neural":[128],"in":[130],"transfer":[132],"learning":[133],"few-shot":[135],"scenes.We":[136],"two":[138],"vocoders,":[140],"AdaMelGAN":[141],"AdaHiFi-GAN.First,":[143],"We":[144],"pre-train":[145],"on":[150,158],"AISHELL3":[151],"CSMSC":[153],"datasets,":[154],"respectively.Then,":[155],"fine-tune":[156],"it":[157],"internal":[160],"VXI-children":[162],"adaptation":[165],"data.The":[166],"empirical":[167],"results":[168],"show":[169],"high-quality":[172],"built":[178],"combining":[180],"vocoder.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}