{"id":"https://openalex.org/W4416799707","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249242","title":"Few-Step Diffusion-Based Voice Conversion Using Consistency Trajectory Models","display_name":"Few-Step Diffusion-Based Voice Conversion Using Consistency Trajectory Models","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799707","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249242"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249242","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":"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":null,"display_name":"Ryuichi Hatakeyama","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Hatakeyama","raw_affiliation_strings":["The University of Electro-Communications,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065514143","display_name":"Toru Nakashika","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005264920","display_name":"Takuya Takahashi","orcid":"https://orcid.org/0000-0001-6523-0622"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Takahashi","raw_affiliation_strings":["The University of Electro-Communications,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Tokyo,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17307165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"507","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8109999895095825,"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":0.8109999895095825,"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":0.07729999721050262,"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":0.03590000048279762,"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/sampling","display_name":"Sampling (signal processing)","score":0.6690999865531921},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.573199987411499},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5271000266075134},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5184999704360962},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4717999994754791},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4293000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.736299991607666},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6690999865531921},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.573199987411499},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5127999782562256},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4553000032901764},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.29420000314712524}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249242","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/G8224511031","display_name":"Establishment of next-generation communication using non-invasive EEG-based linguistic and non-linguistic speech synthesis","funder_award_id":"24H00715","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":8,"referenced_works":["https://openalex.org/W2067295501","https://openalex.org/W2962785568","https://openalex.org/W2962896155","https://openalex.org/W3163475957","https://openalex.org/W3180355996","https://openalex.org/W4225956675","https://openalex.org/W4226320669","https://openalex.org/W4406859138"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,66,91],"study,":[2],"we":[3,93],"propose":[4],"a":[5,21,29,48,53],"voice":[6,30,134],"conversion":[7,31,70,135],"method":[8,130],"that":[9,34,39,55,127],"replaces":[10],"the":[11,16,44,57,76,82,86,95,98,105,128,139],"decoder":[12,54,99],"of":[13,23,36,85,100,107],"DDPMVC":[14,27,132],"with":[15],"consistency":[17],"trajectory":[18],"model":[19,25],"(CTM),":[20],"form":[22],"diffusion":[24,50,108,122],"distillation.":[26],"is":[28,75],"(VC)":[32],"framework":[33,67],"consists":[35],"an":[37],"encoder":[38],"suppresses":[40],"speaker":[41],"information":[42],"from":[43,142],"input":[45],"speech":[46],"through":[47],"forward":[49],"process,":[51],"and":[52,110,116],"generates":[56],"target":[58],"speaker's":[59],"mel-spectrogram":[60],"via":[61],"multi-step":[62],"reverse":[63],"diffusion.":[64],"While":[65],"achieved":[68],"high":[69],"accuracy,":[71],"its":[72],"major":[73],"drawback":[74],"long":[77],"inference":[78,109],"time":[79],"due":[80],"to":[81,120,144],"sequential":[83],"nature":[84],"sampling":[87,118,140],"process.":[88],"To":[89],"address":[90],"issue,":[92],"introduce":[94],"CTM":[96,102],"into":[97],"DDPMVC.":[101],"directly":[103],"predicts":[104],"endpoint":[106],"has":[111],"demonstrated":[112],"improved":[113],"generation":[114],"quality":[115],"faster":[117],"compared":[119],"conventional":[121],"models.":[123],"Experimental":[124],"results":[125],"show":[126],"proposed":[129],"outperforms":[131],"in":[133],"accuracy":[136],"while":[137],"reducing":[138],"steps":[141],"thousands":[143],"just":[145],"10":[146],"steps.":[147]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}