{"id":"https://openalex.org/W4408346014","doi":"https://doi.org/10.1109/icassp49660.2025.10889108","title":"Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model","display_name":"Enhancing Expressive Voice Conversion with Discrete Pitch-Conditioned Flow Matching Model","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408346014","doi":"https://doi.org/10.1109/icassp49660.2025.10889108"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101230918","display_name":"Jialong Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113747251","display_name":"Minghui Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Fang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379388","display_name":"Qian Yang","orcid":"https://orcid.org/0009-0009-8975-6982"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Yang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081447891","display_name":"Wenrui Liu","orcid":"https://orcid.org/0000-0002-9501-7053"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Liu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyan Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051713582","display_name":"Zehai Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehai Tu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067005644","display_name":"Yiwen Guo","orcid":"https://orcid.org/0000-0002-0709-4877"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Guo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":6.6032,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95974461,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991100013256073,"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":0.991100013256073,"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":0.9469000101089478,"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/T12031","display_name":"Speech and dialogue systems","score":0.9246000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6480727195739746},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5886619091033936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5166106820106506},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.48704102635383606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12732800841331482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480727195739746},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5886619091033936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5166106820106506},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.48704102635383606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12732800841331482},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/icassp49660.2025.10889108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2972359262","https://openalex.org/W2972659941","https://openalex.org/W3015805741","https://openalex.org/W3015826515","https://openalex.org/W3024869864","https://openalex.org/W3140429000","https://openalex.org/W3163475957","https://openalex.org/W3163573274","https://openalex.org/W3198217962","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W3213029956","https://openalex.org/W4224916568","https://openalex.org/W4312732823","https://openalex.org/W4372337821","https://openalex.org/W4385822372","https://openalex.org/W4385823264","https://openalex.org/W4392902857","https://openalex.org/W4392903591","https://openalex.org/W4392931276","https://openalex.org/W4401980889","https://openalex.org/W4402111360","https://openalex.org/W4402669711","https://openalex.org/W4402670354","https://openalex.org/W6752307458","https://openalex.org/W6762533536","https://openalex.org/W6776390925","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6803547063","https://openalex.org/W6804125026","https://openalex.org/W6839738141","https://openalex.org/W6846539466","https://openalex.org/W6852870047","https://openalex.org/W6870225445","https://openalex.org/W6870277322","https://openalex.org/W6871686990"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"PFlow-VC,":[3],"a":[4,55,72,84],"conditional":[5],"flow":[6,87],"matching":[7,88],"voice":[8,24,66,107],"conversion":[9,25,67,102,145],"model":[10,76,89,141],"that":[11],"leverages":[12],"fine-grained":[13],"discrete":[14],"pitch":[15,74,80,96],"tokens":[16],"and":[17,45,57,82,130,146],"target":[18],"speaker":[19,33,101],"prompt":[20],"information":[21,81],"for":[22,47,90,99],"expressive":[23],"(VC).":[26],"Previous":[27],"VC":[28],"works":[29],"primarily":[30],"focus":[31],"on":[32,126,153],"conversion,":[34],"with":[35,121],"further":[36],"exploration":[37],"needed":[38],"in":[39,142],"enhancing":[40],"expressiveness":[41,64],"(such":[42],"as":[43],"prosody":[44],"emotion)":[46],"timbre":[48,114,119,123,144],"conversion.":[49],"Unlike":[50],"previous":[51],"methods,":[52],"we":[53,70,112],"adopt":[54],"simple":[56],"efficient":[58],"approach":[59],"to":[60,77],"enhance":[61],"the":[62,100,106,136,139,154],"style":[63,108,147],"of":[65,138],"models.":[68],"Specifically,":[69],"pretrain":[71],"self-supervised":[73],"VQVAE":[75],"discretize":[78],"speaker-irrelevant":[79],"leverage":[83],"masked":[85],"pitch-conditioned":[86],"Mel-spectrogram":[91],"synthesis,":[92],"which":[93],"provides":[94],"in-context":[95],"modeling":[97],"capabilities":[98],"model,":[103],"effectively":[104],"improving":[105],"transfer":[109],"capacity.":[110],"Additionally,":[111],"improve":[113],"similarity":[115],"by":[116],"combining":[117],"global":[118],"embeddings":[120],"time-varying":[122],"tokens.":[124],"Experiments":[125],"unseen":[127],"LibriTTS":[128],"test-clean":[129],"emotional":[131],"speech":[132],"dataset":[133],"ESD":[134],"show":[135],"superiority":[137],"PFlow-VC":[140],"both":[143],"transfer.":[148],"Audio":[149],"samples":[150],"are":[151],"available":[152],"demo":[155],"page":[156],"https://speechai-demo.github.io/PFlow-VC/.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}