{"id":"https://openalex.org/W4403126942","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694576","title":"PAD-VC: A Prosody-Aware Decoder for Any-to-Few Voice Conversion","display_name":"PAD-VC: A Prosody-Aware Decoder for Any-to-Few Voice Conversion","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126942","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694576"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5113417857","display_name":"Arunava Kr. Kalita","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]},{"id":"https://openalex.org/I4210089896","display_name":"Indian Institute of Information Technology Guwahati","ror":"https://ror.org/00bb9ch64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210089896"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arunava Kr. Kalita","raw_affiliation_strings":["IIIT,Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Guwahati,India","institution_ids":["https://openalex.org/I1317621060","https://openalex.org/I4210089896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009881719","display_name":"Christian Dittmar","orcid":"https://orcid.org/0000-0002-3220-2446"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Dittmar","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107744484","display_name":"Paolo Sani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paolo Sani","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019894297","display_name":"Frank Zalkow","orcid":"https://orcid.org/0000-0003-1383-4541"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Zalkow","raw_affiliation_strings":["Fraunhofer IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055742546","display_name":"Rusha Patra","orcid":"https://orcid.org/0000-0003-4293-8251"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]},{"id":"https://openalex.org/I4210089896","display_name":"Indian Institute of Information Technology Guwahati","ror":"https://ror.org/00bb9ch64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210089896"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rusha Patra","raw_affiliation_strings":["IIIT,Guwahati,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT,Guwahati,India","institution_ids":["https://openalex.org/I1317621060","https://openalex.org/I4210089896"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56158189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9409999847412109,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9383000135421753,"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/prosody","display_name":"Prosody","score":0.7680750489234924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703109085559845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6661778688430786}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7680750489234924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703109085559845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6661778688430786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/510148","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/510148","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2123003832","https://openalex.org/W2127141656","https://openalex.org/W2518172956","https://openalex.org/W2962866891","https://openalex.org/W3015805741","https://openalex.org/W3098557217","https://openalex.org/W3161236344","https://openalex.org/W3192737526","https://openalex.org/W3196667132","https://openalex.org/W3198020407","https://openalex.org/W3210679021","https://openalex.org/W4225939199","https://openalex.org/W4296069362","https://openalex.org/W4319862433","https://openalex.org/W4319862723","https://openalex.org/W4322629454","https://openalex.org/W4372260612","https://openalex.org/W4385822773","https://openalex.org/W4388117730","https://openalex.org/W4388273465","https://openalex.org/W4402402635","https://openalex.org/W6628984253","https://openalex.org/W6762533536","https://openalex.org/W6780218876","https://openalex.org/W6927786696"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W187117048","https://openalex.org/W4320472397","https://openalex.org/W2401269021","https://openalex.org/W2145654520","https://openalex.org/W2750037515"],"abstract_inverted_index":{"Voice":[0],"Conversion":[1],"(VC)":[2],"generates":[3],"synthetic":[4],"speech":[5],"from":[6,62],"a":[7,20,29,63],"source":[8,69,87,112],"speaker":[9],"recording,":[10],"preserving":[11],"linguistic":[12,59],"information":[13,78],"and":[14,52,55,79,117],"applying":[15],"the":[16,35,39,68,86,95,99],"voice":[17],"characteristics":[18],"of":[19,38,67,98],"target":[21,100],"speaker.":[22,101],"In":[23],"this":[24],"paper,":[25],"we":[26,73],"propose":[27],"PAD-VC,":[28],"prosody-aware":[30],"VC":[31],"model":[32],"based":[33],"on":[34],"decoder":[36],"part":[37],"ForwardTacotron":[40,107],"architecture.":[41],"We":[42,102],"train":[43],"PAD-VC":[44,105],"with":[45,58],"prosody-related":[46],"features":[47,60,90],"such":[48],"as":[49],"pitch,":[50],"energy,":[51],"voicing":[53],"confidence":[54],"augment":[56],"those":[57],"derived":[61],"phoneme":[64],"posteriorgram":[65],"representation":[66],"utterance.":[70],"This":[71],"way,":[72],"can":[74],"handle":[75],"both":[76],"phonemic":[77],"framewise":[80],"supra-segmental":[81],"features.":[82],"During":[83],"inference":[84],"time,":[85],"speaker\u2019s":[88],"prosody":[89,96],"are":[91],"modified":[92],"to":[93],"match":[94],"statistics":[97],"show":[103],"that":[104],"outperforms":[106],"in":[108],"prosody-cloning":[109],"for":[110],"unseen":[111],"utterances,":[113],"achieving":[114],"higher":[115],"similarity":[116],"naturalness.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}