{"id":"https://openalex.org/W4391021772","doi":"https://doi.org/10.1109/asru57964.2023.10389649","title":"VITS-Based Singing Voice Conversion System with DSPGAN Post-Processing for SVCC2023","display_name":"VITS-Based Singing Voice Conversion System with DSPGAN Post-Processing for SVCC2023","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021772","doi":"https://doi.org/10.1109/asru57964.2023.10389649"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102566429","display_name":"Yiquan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiquan Zhou","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076217439","display_name":"Meng Chen","orcid":"https://orcid.org/0000-0002-4775-5107"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Chen","raw_affiliation_strings":["Tencent Music Entertainment,Lyra Lab,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment,Lyra Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013928267","display_name":"Yi Lei","orcid":"https://orcid.org/0000-0002-9256-9311"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068185614","display_name":"Jihua Zhu","orcid":"https://orcid.org/0000-0002-3081-8781"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhu","raw_affiliation_strings":["Xi’an Jiaotong University,School of Software Engineering,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Software Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101481948","display_name":"Weifeng Zhao","orcid":"https://orcid.org/0009-0007-0533-0120"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Zhao","raw_affiliation_strings":["Tencent Music Entertainment,Lyra Lab,Shenzhen,China","Lyra Lab, Tencent Music Entertainment, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Music Entertainment,Lyra Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Lyra Lab, Tencent Music Entertainment, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976999759674072,"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":0.9894000291824341,"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/singing","display_name":"Singing","score":0.7241861820220947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913968324661255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6601710915565491},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.185997873544693},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05506491661071777}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7241861820220947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913968324661255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6601710915565491},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.185997873544693},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05506491661071777}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2067709094","https://openalex.org/W2118774185","https://openalex.org/W2913668833","https://openalex.org/W2963300588","https://openalex.org/W2963830550","https://openalex.org/W2979476256","https://openalex.org/W2990440871","https://openalex.org/W2998572311","https://openalex.org/W3012498027","https://openalex.org/W3025192522","https://openalex.org/W3092028330","https://openalex.org/W3097952294","https://openalex.org/W3110041771","https://openalex.org/W3170751106","https://openalex.org/W3197943112","https://openalex.org/W3198020407","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4224309976","https://openalex.org/W4226320669","https://openalex.org/W4245692952","https://openalex.org/W4247282941","https://openalex.org/W4283731195","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4301371414","https://openalex.org/W4372338328","https://openalex.org/W4372346850","https://openalex.org/W4385245566","https://openalex.org/W4391021724","https://openalex.org/W6739901393","https://openalex.org/W6769196770","https://openalex.org/W6772349387","https://openalex.org/W6781547035","https://openalex.org/W6783867762","https://openalex.org/W6786824797","https://openalex.org/W6796464841","https://openalex.org/W6803547063","https://openalex.org/W6810889627","https://openalex.org/W6839679458","https://openalex.org/W6839738141","https://openalex.org/W6854646373","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,8,35,47,63,72,75,82,93,96,109,113,146,161],"T02":[4],"team\u2019s":[5],"system":[6,16,140,165],"for":[7],"Singing":[9],"Voice":[10],"Conversion":[11],"Challenge":[12],"2023":[13],"(SVCC2023).":[14],"Our":[15],"entails":[17],"a":[18,25,28,32,53,85,103],"VITS-based":[19],"SVC":[20],"model,":[21],"incorporating":[22],"three":[23],"modules:":[24],"feature":[26,36],"extractor,":[27],"voice":[29,50,57],"converter,":[30],"and":[31,41,67,125,151,155],"postprocessor.":[33],"Specifically,":[34],"extractor":[37],"provides":[38],"F0":[39],"contours":[40],"extracts":[42],"speaker-independent":[43],"linguistic":[44,68],"content":[45,69],"from":[46],"input":[48],"singing":[49],"by":[51],"leveraging":[52],"HuBERT":[54],"model.":[55],"The":[56],"converter":[58],"is":[59,89],"employed":[60],"to":[61,70,79,91,107,112],"recompose":[62],"speaker":[64,99],"timbre,":[65],"F0,":[66],"generate":[71],"waveform":[73],"of":[74,163],"target":[76,98,114],"speaker.":[77,115],"Besides,":[78],"further":[80],"improve":[81],"audio":[83],"quality,":[84],"fine-tuned":[86],"DSPGAN":[87],"vocoder":[88],"introduced":[90],"resynthesise":[92],"waveform.":[94],"Given":[95],"limited":[97],"data,":[100,131],"we":[101],"utilize":[102],"two-stage":[104],"training":[105,127],"strategy":[106],"adapt":[108],"base":[110],"model":[111,117],"During":[116],"adaptation,":[118],"several":[119],"tricks,":[120],"such":[121],"as":[122],"data":[123],"augmentation":[124],"joint":[126],"with":[128],"auxiliary":[129],"singer":[130],"are":[132],"involved.":[133],"Official":[134],"challenge":[135],"results":[136],"show":[137],"that":[138],"our":[139,164],"achieves":[141],"superior":[142],"performance,":[143],"especially":[144],"in":[145,153],"cross-domain":[147],"task,":[148],"ranking":[149],"1st":[150],"2nd":[152],"naturalness":[154],"similarity,":[156],"respectively.":[157],"Further":[158],"ablation":[159],"justifies":[160],"effectiveness":[162],"design.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}