{"id":"https://openalex.org/W4372347381","doi":"https://doi.org/10.1109/icassp49357.2023.10096220","title":"Any-to-Any Voice Conversion with F<sub>0</sub> and Timbre Disentanglement and Novel Timbre Conditioning","display_name":"Any-to-Any Voice Conversion with F<sub>0</sub> and Timbre Disentanglement and Novel Timbre Conditioning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347381","doi":"https://doi.org/10.1109/icassp49357.2023.10096220"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5036744008","display_name":"Sudheer Kovela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sudheer Kovela","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113576287","display_name":"Rafael Valle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042872365","display_name":"Ambrish Dantrey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambrish Dantrey","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9988999962806702,"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/timbre","display_name":"Timbre","score":0.769361138343811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5638175010681152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5624600052833557},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5426971316337585},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.48257461190223694},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4181000292301178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31285202503204346},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17668133974075317},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.15045812726020813},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08977371454238892}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.769361138343811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5638175010681152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5624600052833557},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5426971316337585},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.48257461190223694},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4181000292301178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31285202503204346},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17668133974075317},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.15045812726020813},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08977371454238892},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2395718496","https://openalex.org/W2471520273","https://openalex.org/W2502312327","https://openalex.org/W2937579788","https://openalex.org/W2945478979","https://openalex.org/W2970006822","https://openalex.org/W2972359262","https://openalex.org/W2972667718","https://openalex.org/W2998572311","https://openalex.org/W3083423753","https://openalex.org/W3092028330","https://openalex.org/W3096323553","https://openalex.org/W3097777922","https://openalex.org/W3144417991","https://openalex.org/W3165478005","https://openalex.org/W3168719651","https://openalex.org/W3197273793","https://openalex.org/W3197659778","https://openalex.org/W4225694734","https://openalex.org/W4281736089","https://openalex.org/W6724804524","https://openalex.org/W6761567302","https://openalex.org/W6762533536","https://openalex.org/W6767111847","https://openalex.org/W6772349387","https://openalex.org/W6783867762","https://openalex.org/W6811083959","https://openalex.org/W6838843145"],"related_works":["https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W3109975354","https://openalex.org/W2124576126","https://openalex.org/W2138455584","https://openalex.org/W1984264321","https://openalex.org/W2147073653","https://openalex.org/W2357614930","https://openalex.org/W2008642382","https://openalex.org/W1541822869"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances":[2],"in":[3,103],"voice":[4,15],"conversion":[5,16],"(VC),":[6],"it":[7],"is":[8,99],"still":[9],"challenging":[10],"to":[11,78],"do":[12],"real-time":[13],"one-shot":[14],"with":[17,51,87],"good":[18],"control":[19,79],"over":[20,101],"timbre":[21,85,108],"and":[22,67,84,92,110],"F":[23,62,68,80],"<inf":[24,63,69,81],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[25,64,70,82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[26,65,71,83],".":[27],"In":[28],"this":[29],"work,":[30],"we":[31,75],"present":[32],"a":[33,43,52],"PPG-based":[34],"VC":[35],"model":[36],"that":[37,55,96],"directly":[38],"decodes":[39],"waveforms.":[40],"We":[41],"designed":[42],"speaker":[44,73],"conditioned":[45],"decoder":[46],"based":[47],"on":[48],"HiFi-GAN[1],":[49],"along":[50],"new":[53],"discriminator":[54],"produces":[56],"high":[57,88],"quality":[58],"audio.":[59],"Using":[60],"an":[61],"prenet":[66],"augmented":[72],"encoder,":[74],"are":[76],"able":[77],"independently":[86],"fidelity.":[89],"Our":[90],"objective":[91],"subjective":[93],"evaluations":[94],"show":[95],"our":[97],"method":[98],"preferred":[100],"others":[102],"terms":[104],"of":[105],"audio":[106],"quality,":[107],"similarity":[109],"prosody":[111],"retention.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}