{"id":"https://openalex.org/W3015805741","doi":"https://doi.org/10.1109/icassp40776.2020.9054734","title":"F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder","display_name":"F0-Consistent Many-To-Many Non-Parallel Voice Conversion Via Conditional Autoencoder","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015805741","doi":"https://doi.org/10.1109/icassp40776.2020.9054734","mag":"3015805741"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.07370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030425371","display_name":"Kaizhi Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kaizhi Qian","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Research, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5030425371"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":10.1479,"has_fulltext":false,"cited_by_count":97,"citation_normalized_percentile":{"value":0.98532372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6284","last_page":"6288"},"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":0.9986000061035156,"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":0.9970999956130981,"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":0.8837907910346985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685352087020874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5528770685195923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3613581657409668},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1293121874332428}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8837907910346985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685352087020874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5528770685195923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3613581657409668},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1293121874332428}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.07370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07370","pdf_url":"https://arxiv.org/pdf/2004.07370","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:2004.07370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.07370","pdf_url":"https://arxiv.org/pdf/2004.07370","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W1509691205","https://openalex.org/W2009396100","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2114659828","https://openalex.org/W2123003832","https://openalex.org/W2156142001","https://openalex.org/W2518312472","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2532494225","https://openalex.org/W2608338293","https://openalex.org/W2746474733","https://openalex.org/W2787748320","https://openalex.org/W2788830260","https://openalex.org/W2804998325","https://openalex.org/W2805669069","https://openalex.org/W2887264325","https://openalex.org/W2888932932","https://openalex.org/W2889061305","https://openalex.org/W2889329491","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2962896155","https://openalex.org/W2963830550","https://openalex.org/W2964069186","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W6600438624","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W4220775285"],"abstract_inverted_index":{"Non-parallel":[0],"many-to-many":[1],"voice":[2,123],"conversion":[3,54,124],"remains":[4],"an":[5],"interesting":[6],"but":[7],"challenging":[8],"speech":[9,45,78,144],"processing":[10],"task.":[11],"Many":[12],"style-transfer-inspired":[13],"methods":[14],"such":[15,86],"as":[16,87],"generative":[17],"adversarial":[18],"networks":[19],"(GANs)":[20],"and":[21,44,50,109,120,129,152,156,164],"variational":[22],"autoencoders":[23,32],"(VAEs)":[24],"have":[25],"been":[26],"proposed.":[27],"Recently,":[28],"AutoVC,":[29],"a":[30,58,65,80],"conditional":[31],"(CAEs)":[33],"based":[34],"method":[35],"achieved":[36],"state-of-the-art":[37],"results":[38],"by":[39,55],"disentangling":[40],"the":[41,92,106,116,133,140,149],"speaker":[42,73,130],"identity":[43,61,74,131],"content":[46],"using":[47],"information-constraining":[48],"bottlenecks,":[49],"it":[51],"achieves":[52],"zero-shot":[53],"swapping":[56],"in":[57],"different":[59],"speaker's":[60],"embedding":[62],"to":[63,97,125],"synthesize":[64],"new":[66],"voice.":[67],"However,":[68],"we":[69,118,137],"found":[70],"that":[71],"while":[72],"is":[75],"disentangled":[76],"from":[77],"content,":[79,127],"significant":[81],"amount":[82],"of":[83,105],"prosodic":[84],"information,":[85],"source":[88],"F0,":[89,128],"leaks":[90],"through":[91,162],"bottleneck,":[93],"causing":[94],"target":[95,150],"F0":[96,108,141,146],"fluctuate":[98],"unnaturally.":[99],"Furthermore,":[100],"AutoVC":[101],"has":[102],"no":[103],"control":[104,139],"converted":[107],"thus":[110],"unsuitable":[111],"for":[112],"many":[113],"applications.":[114],"In":[115],"paper,":[117],"modified":[119],"improved":[121],"autoencoder-based":[122],"disentangle":[126],"at":[132],"same":[134],"time.":[135],"Therefore,":[136],"can":[138],"contour,":[142],"generate":[143],"with":[145,148],"consistent":[147],"speaker,":[151],"significantly":[153],"improve":[154],"quality":[155],"similarity.":[157],"We":[158],"support":[159],"our":[160],"improvement":[161],"quantitative":[163],"qualitative":[165],"analysis.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":13}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}