{"id":"https://openalex.org/W4416798711","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249275","title":"CycleSiFiNF-VC: Controllable Non-Parallel Voice Conversion by Neural Formant Manipulation with Improved Cycle-Consistency Loss","display_name":"CycleSiFiNF-VC: Controllable Non-Parallel Voice Conversion by Neural Formant Manipulation with Improved Cycle-Consistency Loss","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798711","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249275"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Sumiharu Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sumiharu Kobayashi","raw_affiliation_strings":["Tohoku University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Tohoku University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University,Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Tohoku University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University,Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34448251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2116","last_page":"2121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9225000143051147,"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":0.9225000143051147,"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/T10863","display_name":"Voice and Speech Disorders","score":0.02969999983906746,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.007300000172108412,"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/formant","display_name":"Formant","score":0.6825000047683716},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5770000219345093},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5397999882698059},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5038999915122986},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4921000003814697},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.42309999465942383},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.3889000117778778},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.3788999915122986}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7577999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077999711036682},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6825000047683716},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8257160697","display_name":null,"funder_award_id":"JP23K21945,JP25K00471,JP23K20725","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2145892079","https://openalex.org/W2476548250","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2962793481","https://openalex.org/W3162512456","https://openalex.org/W3196667132","https://openalex.org/W3197763626","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225956675","https://openalex.org/W4293363567","https://openalex.org/W4372260053","https://openalex.org/W4372262501","https://openalex.org/W4385245566","https://openalex.org/W4385823333","https://openalex.org/W4392903591","https://openalex.org/W4402111357"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"voice":[1,31,89,118],"conversion":[2,32,90,119],"(VC)":[3],"methods":[4],"based":[5],"on":[6],"self-supervised":[7],"learning":[8],"(SSL)":[9],"achieve":[10,150],"high-quality":[11],"and":[12,27,104,131,140],"high":[13],"speaker":[14,135],"similarity":[15,136],"conversions":[16],"but":[17],"face":[18],"challenges":[19],"in":[20],"controlling":[21],"speech":[22,40,53,78,94,106,114,144],"attributes,":[23],"such":[24,55],"as":[25,56],"prosody":[26],"brightness.":[28],"A":[29],"CycleGAN-based":[30],"using":[33,79,96],"mel-cepstral":[34,49,80],"coefficients":[35],"has":[36],"a":[37,63,87],"kind":[38],"of":[39,47,70,113],"controllability":[41],"by":[42],"adjusting":[43],"the":[44,48,67,117,124],"frequency-warping":[45],"parameter":[46],"coefficients.":[50,81],"However,":[51],"unlike":[52],"parameters":[54,95,107,115],"fundamental":[57],"frequency":[58],"or":[59,133],"formants,":[60],"which":[61,146],"have":[62],"one-to-one":[64],"correspondence":[65],"with":[66,151],"physical":[68],"properties":[69],"speech,":[71],"it":[72],"is":[73,147],"difficult":[74,148],"to":[75,138,149],"intuitively":[76],"adjust":[77],"Therefore,":[82],"this":[83],"paper":[84],"proposes":[85],"CycleSiFiNF-VC,":[86],"non-parallel":[88],"method":[91,101,126],"that":[92,123],"transforms":[93,105],"cycle-consistency":[97],"learning.":[98],"Our":[99],"proposed":[100,125],"simultaneously":[102],"predicts":[103],"from":[108],"mel-spectrograms,":[109],"enabling":[110],"individual":[111],"manipulation":[112],"during":[116],"process.":[120],"Experiments":[121],"demonstrate":[122],"achieves":[127],"higher":[128],"synthesis":[129],"quality":[130],"comparable":[132],"superior":[134],"compared":[137],"CycleGAN-VC2,":[139],"enables":[141],"control":[142],"over":[143],"parameters,":[145],"conventional":[152],"methods.":[153]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}