{"id":"https://openalex.org/W4393406152","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482914","title":"End-to-End Cross-Lingual Voice Conversion using CycleGAN for Low Resource Indian Languages","display_name":"End-to-End Cross-Lingual Voice Conversion using CycleGAN for Low Resource Indian Languages","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4393406152","doi":"https://doi.org/10.1109/o-cocosda60357.2023.10482914"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda60357.2023.10482914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5093307080","display_name":"Parth Khadse","orcid":"https://orcid.org/0009-0003-4321-6936"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parth Sanjay Khadse","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083665711","display_name":"Sabyasachi Chandra","orcid":"https://orcid.org/0009-0003-3051-247X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sabyasachi Chandra","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102910914","display_name":"Sankar Mukherjee","orcid":"https://orcid.org/0000-0002-0515-0804"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankar Mukherjee","raw_affiliation_strings":["Phonobyte"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phonobyte","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044762857","display_name":"Puja Bharati","orcid":"https://orcid.org/0009-0000-3468-623X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Puja Bharati","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026317147","display_name":"Debolina Pramanik","orcid":"https://orcid.org/0009-0004-2170-4450"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debolina Pramanik","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093307079","display_name":"Aniket Aitawade","orcid":"https://orcid.org/0009-0009-1210-904X"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aniket Aitawade","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103503442","display_name":"Shyamal Kumar Das Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shyamal Kumar Das Mandal","raw_affiliation_strings":["Indian Institute of Technology,Kharagpur","Indian Institute of Technology, Kharagpur"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Kharagpur","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"Indian Institute of Technology, Kharagpur","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26248256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9749000072479248,"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":0.9118000268936157,"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/computer-science","display_name":"Computer science","score":0.6965732574462891},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5322703123092651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5071635246276855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.370466023683548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31487536430358887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965732574462891},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5322703123092651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5071635246276855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.370466023683548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31487536430358887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda60357.2023.10482914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/o-cocosda60357.2023.10482914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 26th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1570450547","https://openalex.org/W2013996527","https://openalex.org/W2035962301","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2151262064","https://openalex.org/W2476548250","https://openalex.org/W2507912506","https://openalex.org/W2514429423","https://openalex.org/W2574092538","https://openalex.org/W2593414223","https://openalex.org/W2666408839","https://openalex.org/W2785978752","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2938583109","https://openalex.org/W2962793481","https://openalex.org/W2962896155","https://openalex.org/W2963073614","https://openalex.org/W2963539064","https://openalex.org/W2964069186","https://openalex.org/W3008297462","https://openalex.org/W3135780427","https://openalex.org/W4313225764","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2938107654","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0,15],"voice":[1,10,20,55,62,74,78,123,140],"conversion":[2,21,79,100,124,141],"model\u2019s":[3],"goal":[4],"is":[5,22,39,65,105],"to":[6,23,158],"transform":[7,24],"one":[8,66],"individual\u2019s":[9,13],"into":[11,53],"another":[12],"voice.":[14],"main":[16],"objective":[17],"of":[18,27,67,84,93,149,165,173],"cross-lingual":[19,54,77],"the":[25,33,68,82,91,117,150,154],"voices":[26],"speakers":[28,34,95],"speaking":[29,96],"different":[30,36,97],"languages.":[31,98],"As":[32],"speak":[35],"languages,":[37],"there":[38],"acoustic":[40,47],"variability":[41],"in":[42,102,125],"pronunciation,":[43],"prosody,":[44],"and":[45,51,108,144,170],"other":[46],"characteristics":[48],"introducing":[49],"complexity":[50],"challenges":[52],"conversion,":[56],"setting":[57],"it":[58],"apart":[59],"from":[60],"mono-lingual":[61,73],"conversion.":[63,75],"CycleGAN-VC":[64],"state-of-the-art":[69],"models":[70],"developed":[71,121],"for":[72,122,139,167,175],"Most":[76],"systems":[80],"require":[81],"use":[83,89],"ASR,":[85],"but":[86],"here":[87],"we":[88,112],"only":[90],"speech":[92],"two":[94],"Voice":[99],"research":[101],"Indian":[103],"languages":[104],"relatively":[106],"scarce,":[107],"as":[109,111,160,162],"far":[110],"know,":[113],"this":[114,126],"paper":[115,130],"presents":[116],"first":[118],"end-to-end":[119],"model":[120,151],"particular":[127],"context.":[128],"This":[129],"proposes":[131],"using":[132],"a":[133],"Cycle-Consistent":[134],"Generative":[135],"Adversarial":[136],"Network":[137],"(CycleGAN)":[138],"between":[142],"Hindi":[143],"Marathi":[145],"speakers.":[146],"Subjective":[147],"evaluation":[148],"showed":[152],"that":[153],"Mean-Opinion-Score(MOS)":[155],"was":[156],"found":[157],"be":[159],"high":[161],"4":[163],"out":[164,172],"5":[166,174],"speaker":[168,176],"similarity":[169],"3.7":[171],"naturalness.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}