{"id":"https://openalex.org/W4372259892","doi":"https://doi.org/10.1109/icassp49357.2023.10094786","title":"A Synthetic Corpus Generation Method for Neural Vocoder Training","display_name":"A Synthetic Corpus Generation Method for Neural Vocoder Training","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259892","doi":"https://doi.org/10.1109/icassp49357.2023.10094786"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094786","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5103326031","display_name":"Zilin Wang","orcid":"https://orcid.org/0009-0003-6062-3015"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zilin Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346924","display_name":"Peng Liu","orcid":"https://orcid.org/0009-0008-7485-5745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Transsion, Shanghai"],"affiliations":[{"raw_affiliation_string":"Transsion, Shanghai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450139","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0001-7201-1989"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054180274","display_name":"Sipan Li","orcid":"https://orcid.org/0000-0003-3322-0547"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sipan Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","Tencent AI Lab, Shenzhen"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group,Beijing","TAL Education Group, Beijing"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing","institution_ids":["https://openalex.org/I142415962"]},{"raw_affiliation_string":"TAL Education Group, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713778","display_name":"Gang He","orcid":"https://orcid.org/0000-0002-9064-3418"},"institutions":[{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang He","raw_affiliation_strings":["TAL Education Group,Beijing","TAL Education Group, Beijing"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing","institution_ids":["https://openalex.org/I142415962"]},{"raw_affiliation_string":"TAL Education Group, Beijing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Hong Kong SAR, The Chinese University of Hong Kong, China","Peng Cheng Lab, Shenzhen, China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Hong Kong SAR, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Peng Cheng Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","Hong Kong SAR, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Hong Kong SAR, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103326031"],"corresponding_institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0402071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.8519089818000793},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7348543405532837},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5929989814758301},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5137777924537659},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5126304030418396},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.48107481002807617},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4661964476108551},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4653732478618622},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43767985701560974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117175340652466},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10083788633346558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519089818000793},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7348543405532837},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5929989814758301},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5137777924537659},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5126304030418396},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.48107481002807617},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4661964476108551},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4653732478618622},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43767985701560974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117175340652466},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10083788633346558},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094786","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1605424093","https://openalex.org/W1977431865","https://openalex.org/W2152205330","https://openalex.org/W2431874326","https://openalex.org/W2471520273","https://openalex.org/W2584505851","https://openalex.org/W2759171953","https://openalex.org/W2954386831","https://openalex.org/W2972495969","https://openalex.org/W3000389243","https://openalex.org/W3082910224","https://openalex.org/W3092028330","https://openalex.org/W3095617022","https://openalex.org/W3101943858","https://openalex.org/W3103104054","https://openalex.org/W3107087058","https://openalex.org/W3159239022","https://openalex.org/W3162512456","https://openalex.org/W3162770051","https://openalex.org/W3197461241","https://openalex.org/W3202871751","https://openalex.org/W4221152438","https://openalex.org/W4281736089","https://openalex.org/W4285605725","https://openalex.org/W4286950013","https://openalex.org/W4296068763","https://openalex.org/W4296068811","https://openalex.org/W4296069269","https://openalex.org/W4298182583","https://openalex.org/W6771635077","https://openalex.org/W6771763809","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6784488536","https://openalex.org/W6785954764","https://openalex.org/W6794261205","https://openalex.org/W6802142237","https://openalex.org/W6802169104","https://openalex.org/W6838843145","https://openalex.org/W6844035133"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Nowadays,":[0],"neural":[1,15,44,99,142],"vocoders":[2],"are":[3],"preferred":[4],"for":[5,43],"their":[6],"ability":[7],"to":[8,81,101,155],"synthesize":[9],"high-fidelity":[10],"audio.":[11],"However,":[12],"training":[13,111],"a":[14,18,38],"vocoder":[16,45,100,143],"requires":[17],"massive":[19],"corpus":[20,40,96,148],"of":[21,67,117],"high-quality":[22],"real":[23,107],"audio,":[24],"and":[25,78,128,133,159,166],"the":[26,64,83,98,110,115,141,146],"audio":[27,52,68,85,108],"recording":[28],"process":[29],"is":[30],"often":[31],"labor-intensive.":[32],"In":[33],"this":[34],"work,":[35],"we":[36,91,121],"propose":[37],"synthetic":[39,51,95,147],"generation":[41],"method":[42,152],"training,":[46],"which":[47],"can":[48,153],"easily":[49],"generate":[50],"with":[53,87,145],"an":[54],"unlimited":[55],"number":[56],"at":[57],"nearly":[58],"no":[59],"cost.":[60],"We":[61],"explicitly":[62],"model":[63],"prior":[65],"characteristics":[66],"from":[69],"multiple":[70,156],"target":[71,157],"domains":[72],"simultaneously":[73],"(e.g.,":[74],"speeches,":[75],"singing":[76,162],"voices,":[77],"instrumental":[79,167],"pieces)":[80],"equip":[82],"generated":[84],"data":[86],"these":[88],"characteristics.":[89],"And":[90],"show":[92,139],"that":[93,140],"our":[94,118,151],"allows":[97],"achieve":[102],"competitive":[103],"results":[104,138],"without":[105],"any":[106],"in":[109,131],"process.":[112],"To":[113],"validate":[114],"effectiveness":[116],"proposed":[119],"method,":[120],"performed":[122],"empirical":[123],"experiments":[124],"on":[125],"both":[126],"speech":[127],"music":[129],"utterances":[130],"subjective":[132],"objective":[134],"metrics.":[135],"The":[136],"experimental":[137],"trained":[144],"produced":[149],"by":[150],"generalize":[154],"scenarios":[158],"has":[160],"excellent":[161],"voice":[163],"(MOS:":[164,169],"4.20)":[165],"piece":[168],"4.00)":[170],"synthesis":[171],"results.":[172]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}