{"id":"https://openalex.org/W3162879338","doi":"https://doi.org/10.1109/icassp39728.2021.9413959","title":"Crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder","display_name":"Crank: An Open-Source Software for Nonparallel Voice Conversion Based on Vector-Quantized Variational Autoencoder","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162879338","doi":"https://doi.org/10.1109/icassp39728.2021.9413959","mag":"3162879338"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan","TARVO, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Nagoya University,Japan","TARVO, Inc., Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan","TARVO, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"TARVO, Inc., Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5934","last_page":"5938"},"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":0.9980999827384949,"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":0.9925000071525574,"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/autoencoder","display_name":"Autoencoder","score":0.9223376512527466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7438946962356567},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5460056662559509},{"id":"https://openalex.org/keywords/crank","display_name":"Crank","score":0.4863279461860657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4855194091796875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44459986686706543},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3730385899543762}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9223376512527466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7438946962356567},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5460056662559509},{"id":"https://openalex.org/C198994188","wikidata":"https://www.wikidata.org/wiki/Q857558","display_name":"Crank","level":3,"score":0.4863279461860657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855194091796875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44459986686706543},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3730385899543762},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413959","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1524333225","https://openalex.org/W2012086895","https://openalex.org/W2052871313","https://openalex.org/W2120847449","https://openalex.org/W2156142001","https://openalex.org/W2242818861","https://openalex.org/W2510867321","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2548275288","https://openalex.org/W2598638573","https://openalex.org/W2752796333","https://openalex.org/W2800289214","https://openalex.org/W2937579788","https://openalex.org/W2946555236","https://openalex.org/W2949382160","https://openalex.org/W2950776302","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2963799213","https://openalex.org/W2964069186","https://openalex.org/W2971074500","https://openalex.org/W2972394484","https://openalex.org/W2972544500","https://openalex.org/W2972849140","https://openalex.org/W2994715919","https://openalex.org/W2996414377","https://openalex.org/W3002433751","https://openalex.org/W3015338123","https://openalex.org/W3082130377","https://openalex.org/W3092246895","https://openalex.org/W3093058615","https://openalex.org/W3095361818","https://openalex.org/W3096567388","https://openalex.org/W3100378519","https://openalex.org/W3101689408","https://openalex.org/W3199367817","https://openalex.org/W6631362777","https://openalex.org/W6690026940","https://openalex.org/W6729482032","https://openalex.org/W6762931180","https://openalex.org/W6771070734","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W2909431601","https://openalex.org/W4294770367"],"abstract_inverted_index":{"In":[0,170],"this":[1,69,72,118,171],"paper,":[2,172],"we":[3,19,74,101,173],"present":[4],"an":[5,22],"open-source":[6,23,78],"software":[7,25,80],"for":[8,127],"developing":[9],"a":[10,63,76,92,103],"nonparallel":[11,93],"voice":[12],"conversion":[13,65,87],"(VC)":[14],"system":[15],"named":[16,32],"crank.":[17],"Although":[18],"have":[20],"released":[21],"VC":[24,37,79,99,129],"based":[26,167],"on":[27,168],"the":[28,35,86,98,111,133],"Gaussian":[29],"mixture":[30],"model":[31,62,85],"sprocket":[33],"in":[34,71,117,178],"last":[36],"Challenge,":[38],"it":[39,49,150],"is":[40,50,151],"not":[41],"straightforward":[42],"to":[43,52,61,84,153],"apply":[44],"any":[45],"speech":[46,94],"corpus":[47],"because":[48],"necessary":[51],"prepare":[53],"parallel":[54],"utterances":[55],"of":[56,113,135],"source":[57],"and":[58,146,162,180],"target":[59],"speakers":[60],"statistical":[64],"function.":[66],"To":[67,108],"address":[68],"issue,":[70],"study,":[73],"developed":[75,116,177],"new":[77],"that":[81],"enables":[82],"users":[83],"function":[88],"by":[89,184],"using":[90],"only":[91],"corpus.":[95],"For":[96],"implementing":[97],"software,":[100],"used":[102],"vector-quantized":[104],"variational":[105],"autoencoder":[106],"(VQVAE).":[107],"rapidly":[109],"examine":[110],"effectiveness":[112],"recent":[114],"technologies":[115],"research":[119],"field,":[120],"crank":[121,179],"also":[122],"supports":[123],"several":[124],"representative":[125,175],"works":[126],"autoencoder-based":[128],"methods":[130],"such":[131,158],"as":[132,159],"use":[134],"hierarchical":[136],"architectures,":[137,139],"cyclic":[138],"generative":[140],"adversarial":[141,144],"networks,":[142],"speaker":[143],"training,":[145],"neural":[147],"vocoders.":[148],"Moreover,":[149],"possible":[152],"automatically":[154],"estimate":[155],"objective":[156,185],"measures":[157],"mel-cepstrum":[160],"distortion":[161],"pseudo":[163],"mean":[164],"opinion":[165],"score":[166],"MOSNet.":[169],"describe":[174],"functions":[176],"make":[181],"brief":[182],"comparisons":[183],"evaluations.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}