{"id":"https://openalex.org/W4401609118","doi":"https://doi.org/10.1109/icasspw62465.2024.10626687","title":"Scaling Nvidia\u2019s Multi-Speaker Multi-Lingual TTS Systems With Zero-Shot TTS to Indic Languages","display_name":"Scaling Nvidia\u2019s Multi-Speaker Multi-Lingual TTS Systems With Zero-Shot TTS to Indic Languages","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609118","doi":"https://doi.org/10.1109/icasspw62465.2024.10626687"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626687","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":["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/A5015337981","display_name":"Akshit Arora","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akshit Arora","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058296176","display_name":"Rohan Badlani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Badlani","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327702","display_name":"Sungwon Kim","orcid":"https://orcid.org/0000-0002-9371-8884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungwon Kim","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":"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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73313215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.958299994468689,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.958299994468689,"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/T12031","display_name":"Speech and dialogue systems","score":0.9531000256538391,"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/zero","display_name":"Zero (linguistics)","score":0.649326741695404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6477159261703491},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6198859214782715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4726463854312897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16715866327285767},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1329401433467865},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.053276628255844116}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.649326741695404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6477159261703491},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6198859214782715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4726463854312897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16715866327285767},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1329401433467865},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.053276628255844116},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10626687","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2972359262","https://openalex.org/W4212774754","https://openalex.org/W4372260209","https://openalex.org/W4385823392","https://openalex.org/W6783867762","https://openalex.org/W6936113694"],"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/W4395014643"],"abstract_inverted_index":{"In":[0,23,46],"this":[1],"paper,":[2],"we":[3,28,49],"describe":[4],"the":[5,12,60],"TTS":[6,17,35,56],"models":[7],"developed":[8],"by":[9,36,57],"NVIDIA":[10],"for":[11,73],"MMITS-VC":[13],"(Multi-speaker,":[14],"Multi-lingual":[15],"Indic":[16],"with":[18,91],"Voice":[19],"Cloning)":[20],"2024":[21],"Challenge.":[22],"Tracks":[24,80],"1":[25,81],"and":[26,82,97],"2,":[27,83],"utilize":[29,50],"RAD-MMM":[30,76],"[1]":[31],"to":[32,53],"perform":[33,54],"few-shot":[34],"training":[37,58],"additionally":[38],"on":[39,59,79,88],"5":[40],"minutes":[41],"of":[42,102],"target":[43],"speaker":[44,98],"data.":[45],"Track":[47,89],"3,":[48,90],"P-Flow":[51,85],"[2]":[52],"zero-shot":[55],"challenge":[61],"dataset":[62],"as":[63,65],"well":[64],"external":[66],"datasets.":[67],"We":[68],"use":[69],"HiFi-GAN":[70],"[3]":[71],"vocoders":[72],"all":[74],"submissions.":[75],"performs":[77],"competitively":[78],"while":[84],"ranks":[86],"first":[87],"mean":[92],"opinion":[93],"score":[94,100],"(MOS)":[95],"4.4":[96],"similarity":[99],"(SMOS)":[101],"3.62.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}