{"id":"https://openalex.org/W4401609519","doi":"https://doi.org/10.1109/icasspw62465.2024.10627128","title":"Investigating Self-Supervised Features for Expressive, Multilingual Voice Conversion","display_name":"Investigating Self-Supervised Features for Expressive, Multilingual Voice Conversion","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609519","doi":"https://doi.org/10.1109/icasspw62465.2024.10627128"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.08278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093887362","display_name":"\u00c1lvaro Mart\u00edn-Cortinas","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"\u00c1lvaro Mart\u00edn-Cortinas","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087232606","display_name":"Daniel S\u00e1ez-Trigueros","orcid":"https://orcid.org/0000-0001-9623-7472"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S\u00e1ez-Trigueros","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045200344","display_name":"Grzegorz Beringer","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grzegorz Beringer","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055920967","display_name":"Iv\u00e1n Vall\u00e9s-\u1e54erez","orcid":"https://orcid.org/0000-0002-7588-5777"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iv\u00e1n Vall\u00e9s-P\u00e9rez","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092579799","display_name":"Biel Tura-Vecino","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biel Tura-Vecino","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031116817","display_name":"Adam Gabry\u015b","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Gabry\u015b","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060480943","display_name":"Piotr Bili\u0144ski","orcid":"https://orcid.org/0000-0002-7023-3438"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Bili\u0144ski","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon AGI"],"affiliations":[{"raw_affiliation_string":"Amazon AGI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5093887362"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11174443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9779000282287598,"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":0.9779000282287598,"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":0.7787594199180603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6047146916389465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5064929723739624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3837563395500183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787594199180603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6047146916389465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5064929723739624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3837563395500183}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627128","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10627128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.08278","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08278","pdf_url":"https://arxiv.org/pdf/2505.08278","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.08278","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08278","pdf_url":"https://arxiv.org/pdf/2505.08278","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401609519.pdf","grobid_xml":"https://content.openalex.org/works/W4401609519.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2121044470","https://openalex.org/W2518172956","https://openalex.org/W2804998325","https://openalex.org/W2890964092","https://openalex.org/W2937579788","https://openalex.org/W2962788625","https://openalex.org/W2963539064","https://openalex.org/W2972359262","https://openalex.org/W2973053330","https://openalex.org/W3095410713","https://openalex.org/W3097881066","https://openalex.org/W3098557217","https://openalex.org/W3134921434","https://openalex.org/W3140429000","https://openalex.org/W3161627112","https://openalex.org/W3194143312","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225316945","https://openalex.org/W4226380987","https://openalex.org/W4229024115","https://openalex.org/W4287889585","https://openalex.org/W4311000453","https://openalex.org/W4319862479","https://openalex.org/W4319862652","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6762533536","https://openalex.org/W6771467084","https://openalex.org/W6838843145","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,75,111],"(VC)":[2],"systems":[3],"are":[4,35],"widely":[5],"used":[6],"for":[7],"several":[8],"applications,":[9],"from":[10],"speaker":[11,51,63,95,127,131],"anonymisation":[12],"to":[13,31,38,62,99,105,118],"personalised":[14],"speech":[15],"synthesis.":[16],"Supervised":[17],"approaches":[18,34],"learn":[19],"a":[20,57,100,134],"mapping":[21],"between":[22],"different":[23],"speakers":[24],"using":[25],"parallel":[26],"data,":[27],"which":[28,43,102],"is":[29,44,56,97,103],"expensive":[30],"produce.":[32],"Unsupervised":[33],"typically":[36],"trained":[37,104],"reconstruct":[39,106],"the":[40,47,50,78,87,107,120,125,130],"input":[41],"signal,":[42],"composed":[45],"of":[46,80,86,90,124,133],"content":[48,123],"and":[49,59,122],"information.":[52],"Disentangling":[53],"these":[54],"components":[55],"challenge":[58],"often":[60],"leads":[61],"leakage":[64],"or":[65],"prosodic":[66],"information":[67],"removal.":[68],"In":[69],"this":[70,115],"paper,":[71],"we":[72],"explore":[73],"voice":[74,110],"by":[76],"leveraging":[77],"potential":[79],"self-supervised":[81],"learning":[82],"(SSL).":[83],"A":[84],"combination":[85],"latent":[88],"representations":[89],"SSL":[91],"models,":[92],"concatenated":[93],"with":[94],"embeddings,":[96],"fed":[98],"vocoder":[101],"input.":[108],"Zero-shot":[109],"results":[112],"show":[113],"that":[114],"approach":[116],"allows":[117],"keep":[119],"prosody":[121],"source":[126],"while":[128],"matching":[129],"similarity":[132],"VC":[135],"system":[136],"based":[137],"on":[138],"phonetic":[139],"posteriorgrams":[140],"(PPGs).":[141]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}