{"id":"https://openalex.org/W2996414377","doi":"https://doi.org/10.1109/taslp.2019.2960721","title":"Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations","display_name":"Non-Parallel Sequence-to-Sequence Voice Conversion With Disentangled Linguistic and Speaker Representations","publication_year":2019,"publication_date":"2019-12-19","ids":{"openalex":"https://openalex.org/W2996414377","doi":"https://doi.org/10.1109/taslp.2019.2960721","mag":"2996414377"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2960721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2960721","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.10508","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jing-Xuan Zhang","orcid":"https://orcid.org/0000-0003-4341-3174"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing-Xuan Zhang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-4341-3174","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":null,"display_name":"Li-Rong Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":5.6476,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.96709154,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"540","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8680999875068665,"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":0.8680999875068665,"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":0.05220000073313713,"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/T10863","display_name":"Voice and Speech Disorders","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.733299970626831},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4772999882698059},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4771000146865845},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46540001034736633},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4375},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.33570000529289246}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.733299970626831},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7231000065803528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199000120162964},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46540001034736633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.33570000529289246},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30000001192092896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2019.2960721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2960721","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.10508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.10508","pdf_url":"https://arxiv.org/pdf/1906.10508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.10508","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.10508","pdf_url":"https://arxiv.org/pdf/1906.10508","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8663906801","display_name":"\u9762\u5411\u8bed\u97f3\u5408\u6210\u7684\u795e\u7ecf\u7f51\u7edc\u58f0\u7801\u5668\u7814\u7a76","funder_award_id":"61871358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W156398200","https://openalex.org/W1509691205","https://openalex.org/W1902237438","https://openalex.org/W2009272428","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2067234399","https://openalex.org/W2086796102","https://openalex.org/W2100819376","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2152974894","https://openalex.org/W2153425803","https://openalex.org/W2157331557","https://openalex.org/W2157364932","https://openalex.org/W2157412983","https://openalex.org/W2161135987","https://openalex.org/W2161476805","https://openalex.org/W2327501763","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2576309025","https://openalex.org/W2804998325","https://openalex.org/W2886769154","https://openalex.org/W2888922217","https://openalex.org/W2889329491","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2902070858","https://openalex.org/W2937020545","https://openalex.org/W2937579788","https://openalex.org/W2939131199","https://openalex.org/W2963290645","https://openalex.org/W2963830550","https://openalex.org/W2964069186","https://openalex.org/W2964243274","https://openalex.org/W4240592325","https://openalex.org/W4245885054","https://openalex.org/W6602386084","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6685352114","https://openalex.org/W6735509194","https://openalex.org/W6735927292","https://openalex.org/W6736811364","https://openalex.org/W6736996214","https://openalex.org/W6737196085","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6798679566","https://openalex.org/W6936113694","https://openalex.org/W6947763825"],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1],"presents":[2],"a":[3,119,131,135,139,146],"method":[4,185,197,209],"of":[5,37,56,77,90,145,170,206],"sequence-to-sequence":[6],"(seq2seq)":[7],"voice":[8,28,195,217],"conversion":[9,29,148,175,196,218],"using":[10,134,142],"non-parallel":[11,194],"training":[12,78,96],"data.":[13],"In":[14],"this":[15],"method,":[16],"disentangled":[17,68],"linguistic":[18,35,69,88,108],"and":[19,27,138,155,173,189],"speaker":[20,43,104,111,120],"representations":[21,36,44,70,89,112],"are":[22,80,113,125,162,167],"extracted":[23,114],"from":[24,106,115],"acoustic":[25,160],"features,":[26],"is":[30,51,63,98],"achieved":[31],"by":[32,118,127],"preserving":[33],"the":[34,42,46,54,67,84,107,143,152,156,192,204,213],"source":[38],"utterances":[39],"while":[40],"replacing":[41],"with":[45,71],"target":[47],"ones.":[48],"Our":[49],"model":[50,123],"built":[52],"under":[53],"framework":[55],"encoder-decoder":[57],"neural":[58,164],"networks.":[59],"A":[60],"recognition":[61,153],"encoder":[62,154],"designed":[64],"to":[65,82,100,212],"learn":[66],"two":[72],"strategies.":[73],"First,":[74],"phoneme":[75],"transcriptions":[76],"data":[79],"introduced":[81],"provide":[83],"references":[85],"for":[86,158],"leaning":[87],"audio":[91,116],"signals.":[92],"Second,":[93],"an":[94],"adversarial":[95],"strategy":[97],"employed":[99],"further":[101],"wipe":[102],"out":[103],"information":[105],"representations.":[109],"Meanwhile,":[110],"signals":[117],"encoder.":[121],"The":[122],"parameters":[124],"estimated":[126],"two-stage":[128],"training,":[129],"including":[130],"pre-training":[132],"stage":[133,141],"multi-speaker":[136],"dataset":[137,144],"fine-tuning":[140],"specific":[147],"pair.":[149],"Since":[150],"both":[151],"decoder":[157],"recovering":[159],"features":[161],"seq2seq":[163,216],"networks,":[165],"there":[166],"no":[168],"constrains":[169],"frame":[171],"alignment":[172],"frame-by-frame":[174],"in":[176,198],"our":[177,184,207],"proposed":[178,208],"method.":[179,219],"Experimental":[180],"results":[181],"showed":[182],"that":[183],"obtained":[186],"higher":[187],"similarity":[188],"naturalness":[190],"than":[191],"best":[193],"Voice":[199],"Conversion":[200],"Challenge":[201],"2018.":[202],"Besides,":[203],"performance":[205],"was":[210],"closed":[211],"state-of-the-art":[214],"parallel":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-12-26T00:00:00"}