{"id":"https://openalex.org/W3198530218","doi":"https://doi.org/10.21437/interspeech.2021-137","title":"CVC: Contrastive Learning for Non-Parallel Voice Conversion","display_name":"CVC: Contrastive Learning for Non-Parallel Voice Conversion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198530218","doi":"https://doi.org/10.21437/interspeech.2021-137","mag":"3198530218"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5054695986","display_name":"Tingle Li","orcid":"https://orcid.org/0000-0003-1654-8030"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Tingle Li","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, China","Shanghai Qi Zhi Institute, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605131","display_name":"Yichen Liu","orcid":"https://orcid.org/0000-0002-6681-5582"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Liu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017581594","display_name":"Chenxu Hu","orcid":null},"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/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxu Hu","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, China","College of Computer Science and Technology, Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104009095","display_name":"Hang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":true,"raw_author_name":"Hang Zhao","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University, China","Shanghai Qi Zhi Institute, China"],"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, China","institution_ids":["https://openalex.org/I4210122302"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104009095"],"corresponding_institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2189,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79364435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9933000206947327,"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":0.7730532884597778},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46729806065559387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730532884597778},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46729806065559387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":29,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2118154032","https://openalex.org/W2152790380","https://openalex.org/W2157412983","https://openalex.org/W2194775991","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2808706139","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2963073614","https://openalex.org/W2963539064","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2972544500","https://openalex.org/W2972667718","https://openalex.org/W3005680577","https://openalex.org/W3015338123","https://openalex.org/W3030987249","https://openalex.org/W3034089333","https://openalex.org/W3095361818","https://openalex.org/W3095936335","https://openalex.org/W3110137169","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W4361745739"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Cycle":[0],"consistent":[1],"generative":[2],"adversarial":[3,38],"network":[4],"(CycleGAN)":[5],"and":[6,27,77],"variational":[7],"autoencoder":[8],"(VAE)":[9],"based":[10],"models":[11],"have":[12],"gained":[13],"popularity":[14],"in":[15,88],"non-parallel":[16],"voice":[17,41,67,90],"conversion":[18,94],"recently.However,":[19],"they":[20],"often":[21],"suffer":[22],"from":[23,95],"difficult":[24],"training":[25,54,82],"process":[26],"unsatisfactory":[28],"results.In":[29],"this":[30],"paper,":[31],"we":[32],"propose":[33],"CVC,":[34],"a":[35],"contrastive":[36,60],"learning-based":[37],"approach":[39],"for":[40],"conversion.Compared":[42],"to":[43,64],"previous":[44],"CycleGAN-based":[45],"methods,":[46],"CVC":[47,69],"only":[48],"requires":[49],"an":[50],"efficient":[51],"one-way":[52],"GAN":[53],"by":[55],"taking":[56],"the":[57,93],"advantage":[58],"of":[59],"learning.When":[61],"it":[62],"comes":[63],"nonparallel":[65],"one-to-one":[66],"conversion,":[68,91],"is":[70],"on":[71],"par":[72],"or":[73],"better":[74],"than":[75],"CycleGAN":[76],"VAE":[78],"while":[79],"effectively":[80],"reducing":[81],"time.CVC":[83],"further":[84],"demonstrates":[85],"superior":[86],"performance":[87],"manyto-one":[89],"enabling":[92],"unseen":[96],"speakers.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}