{"id":"https://openalex.org/W2804998325","doi":"https://doi.org/10.1109/icassp.2018.8461384","title":"Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors","display_name":"Non-Parallel Voice Conversion Using Variational Autoencoders Conditioned by Phonetic Posteriorgrams and D-Vectors","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2804998325","doi":"https://doi.org/10.1109/icassp.2018.8461384","mag":"2804998325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110780218","display_name":"Kyosuke Nishida","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kyosuke Nishida","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5083394213"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":15.7997,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99155775,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5274","last_page":"5278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9955000281333923,"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/naturalness","display_name":"Naturalness","score":0.820109486579895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853972911834717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7198969721794128},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5483636260032654},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5387438535690308},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5014257431030273},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4164614975452423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40971359610557556},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40929943323135376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36029890179634094},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11961290240287781}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.820109486579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853972911834717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7198969721794128},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5483636260032654},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5387438535690308},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5014257431030273},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4164614975452423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40971359610557556},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40929943323135376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36029890179634094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11961290240287781},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2046056978","https://openalex.org/W2049686551","https://openalex.org/W2108501770","https://openalex.org/W2114925438","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2146502635","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2156387975","https://openalex.org/W2475998840","https://openalex.org/W2516321201","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2556467266","https://openalex.org/W2759925408","https://openalex.org/W2949416428","https://openalex.org/W2963223306","https://openalex.org/W2963403664","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6681435938","https://openalex.org/W6682889407","https://openalex.org/W6688384872","https://openalex.org/W6725896364","https://openalex.org/W6726528559","https://openalex.org/W6728445508","https://openalex.org/W6730333270","https://openalex.org/W6744965914"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"This":[0],"paper":[1,57,109],"proposes":[2,58],"novel":[3],"frameworks":[4],"for":[5,139,147,160],"non-parallel":[6,23,61,115,195],"voice":[7],"conversion":[8],"(VC)":[9],"using":[10,22,158],"variational":[11],"autoencoders":[12],"(VAEs).":[13],"Although":[14],"conventional":[15,113,153],"VAE-based":[16,60,114,193],"VC":[17,62,95,116,119,149],"models":[18,96],"can":[19,91,121,188],"be":[20,189],"trained":[21],"speech":[24,35,75,144],"corpora":[25,145],"with":[26],"given":[27,86],"speaker":[28,68,137,154,162,175,184],"representations,":[29],"phonetic":[30,72,78,83],"contents":[31,73,84],"of":[32,40,49,74,102,177],"the":[33,50,54,67,82,88,94,106,112,161,178,192],"converted":[34,179],"tend":[36],"to":[37,117,135,191],"vanish":[38],"because":[39],"an":[41],"over-regularization":[42],"issue":[43],"often":[44],"observed":[45],"in":[46,143],"latent":[47,100],"variables":[48],"VAEs.":[51],"To":[52],"overcome":[53],"issue,":[55],"this":[56,108],"a":[59],"conditioned":[63],"by":[64],"not":[65,141],"only":[66],"representations":[69,138],"but":[70],"also":[71,110],"represented":[76],"as":[77],"posteriorgrams":[79],"(PPGs).":[80],"Since":[81],"are":[85],"during":[87],"training,":[89],"we":[90],"expect":[92],"that":[93,120,167],"effectively":[97],"learn":[98],"speaker-independent":[99],"features":[101],"speech.":[103],"Focusing":[104],"on":[105],"point,":[107],"extends":[111],"many-to-many":[118,194],"convert":[122],"arbitrary":[123,128],"speakers'":[124,129],"characteristics":[125],"into":[126],"another":[127],"ones.":[130],"We":[131],"investigate":[132],"two":[133],"methods":[134],"estimate":[136],"speakers":[140],"included":[142],"used":[146],"training":[148],"models:":[150],"1)":[151,168],"adapting":[152],"codes,":[155],"and":[156,174,181,186],"2)":[157,182],"d-vectors":[159,187],"representations.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"PPGs":[169],"successfully":[170],"improve":[171],"both":[172,183],"naturalness":[173],"similarity":[176],"speech,":[180],"codes":[185],"adopted":[190],"VC.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}