{"id":"https://openalex.org/W4372260209","doi":"https://doi.org/10.1109/icassp49357.2023.10096613","title":"Vani: Very-Lightweight Accent-Controllable TTS for Native And Non-Native Speakers With Identity Preservation","display_name":"Vani: Very-Lightweight Accent-Controllable TTS for Native And Non-Native Speakers With Identity Preservation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260209","doi":"https://doi.org/10.1109/icassp49357.2023.10096613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096613","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096613","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/A5058296176","display_name":"Rohan Badlani","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rohan Badlani","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015337981","display_name":"Akshit Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Akshit Arora","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0001-9191-5684"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113576287","display_name":"Rafael Valle","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rafael Valle","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016107863","display_name":"Kevin J. Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin J. Shih","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068457267","display_name":"Jo\u00e3o Felipe Santos","orcid":"https://orcid.org/0000-0003-3934-3943"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Felipe Santos","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["Nvidia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1304085615"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/stress","display_name":"Stress (linguistics)","score":0.8675931692123413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7241240739822388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.662752091884613},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5762211084365845},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.530856192111969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573172926902771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4445456862449646},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41775205731391907},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41524454951286316},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3405095934867859},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09381610155105591}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8675931692123413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7241240739822388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.662752091884613},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5762211084365845},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.530856192111969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573172926902771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4445456862449646},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41775205731391907},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41524454951286316},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3405095934867859},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09381610155105591},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096613","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096613","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/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3205878676","https://openalex.org/W4385823392","https://openalex.org/W6778083308"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"We":[0,40,86],"introduce":[1],"VANI,":[2],"a":[3,72],"very":[4],"lightweight":[5,96],"multi-lingual":[6],"accent":[7,81],"controllable":[8],"speech":[9,38,60],"synthesis":[10],"system.":[11],"Our":[12,65],"model":[13,66,91,98],"builds":[14],"upon":[15],"disentanglement":[16],"strategies":[17],"proposed":[18],"in":[19,61],"RADMMM[1]":[20],"and":[21,29,34,78,95,102],"supports":[22,67],"explicit":[23],"control":[24],"of":[25,52,71,82,104],"accent,":[26],"language,":[27],"speaker":[28,73],"fine-grained":[30],"F<inf":[31],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[32],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[33],"energy":[35],"features":[36],"for":[37,47,92,99],"synthesis.":[39],"utilize":[41,87],"the":[42,69,79,83,88,105],"Indic":[43],"languages":[44],"dataset,":[45],"released":[46],"LIMMITS":[48],"2023":[49],"as":[50],"part":[51],"ICASSP":[53],"Signal":[54],"Processing":[55],"Grand":[56],"Challenge,":[57],"to":[58],"synthesize":[59],"3":[62,103],"different":[63],"languages.":[64],"transferring":[68],"language":[70],"while":[74],"retaining":[75],"their":[76],"voice":[77],"native":[80],"target":[84],"language.":[85],"large-parameter":[89],"RADMMM":[90],"Track":[93,100],"1":[94],"VANI":[97],"2":[101],"competition.":[106]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
