{"id":"https://openalex.org/W4388820765","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317438","title":"FID-RPRGAN-VC: Fr\u00e9chet Inception Distance Loss based Region-wise Position Normalized Relativistic GAN for Non-Parallel Voice Conversion","display_name":"FID-RPRGAN-VC: Fr\u00e9chet Inception Distance Loss based Region-wise Position Normalized Relativistic GAN for Non-Parallel Voice Conversion","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820765","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317438"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102798862","display_name":"Sandipan Dhar","orcid":"https://orcid.org/0000-0002-3606-6664"},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandipan Dhar","raw_affiliation_strings":["National Institute of Technology,Durgapur,India","National Institute of Technology, Durgapur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Durgapur,India","institution_ids":["https://openalex.org/I155837530"]},{"raw_affiliation_string":"National Institute of Technology, Durgapur, India","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048733804","display_name":"Md. Tousin Akhter","orcid":null},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"MD. Tousin Akhter","raw_affiliation_strings":["National Institute of Technology,Durgapur,India","National Institute of Technology, Durgapur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Durgapur,India","institution_ids":["https://openalex.org/I155837530"]},{"raw_affiliation_string":"National Institute of Technology, Durgapur, India","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070345951","display_name":"Padmanabha Banerjee","orcid":"https://orcid.org/0009-0003-1254-6270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Padmanabha Banerjee","raw_affiliation_strings":["Jalpaiguri Government Engineering College,India","Jalpaiguri Government Engineering College, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jalpaiguri Government Engineering College,India","institution_ids":[]},{"raw_affiliation_string":"Jalpaiguri Government Engineering College, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055489209","display_name":"Nanda Dulal Jana","orcid":"https://orcid.org/0000-0003-0631-9912"},"institutions":[{"id":"https://openalex.org/I155837530","display_name":"National Institute of Technology Durgapur","ror":"https://ror.org/04ds0jm32","country_code":"IN","type":"education","lineage":["https://openalex.org/I155837530"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nanda Dulal Jana","raw_affiliation_strings":["National Institute of Technology,Durgapur,India","National Institute of Technology, Durgapur, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Durgapur,India","institution_ids":["https://openalex.org/I155837530"]},{"raw_affiliation_string":"National Institute of Technology, Durgapur, India","institution_ids":["https://openalex.org/I155837530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000078546","display_name":"Swagatam Das","orcid":"https://orcid.org/0000-0001-6843-4508"},"institutions":[{"id":"https://openalex.org/I6498739","display_name":"Indian Statistical Institute","ror":"https://ror.org/00q2w1j53","country_code":"IN","type":"education","lineage":["https://openalex.org/I6498739"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swagatam Das","raw_affiliation_strings":["Indian Statistical Institute,Kolkata,India","Indian Statistical Institute, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Statistical Institute,Kolkata,India","institution_ids":["https://openalex.org/I6498739"]},{"raw_affiliation_string":"Indian Statistical Institute, Kolkata, India","institution_ids":["https://openalex.org/I6498739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9979000091552734,"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":0.9918000102043152,"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/naturalness","display_name":"Naturalness","score":0.8701809048652649},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8108771443367004},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6855198740959167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5739757418632507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5467220544815063},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.43768712878227234},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.430071622133255},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4139418601989746},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21953746676445007},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18411967158317566},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12331166863441467},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11756816506385803}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8701809048652649},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8108771443367004},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6855198740959167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5739757418632507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5467220544815063},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.43768712878227234},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.430071622133255},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4139418601989746},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21953746676445007},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18411967158317566},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12331166863441467},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11756816506385803},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W2060352980","https://openalex.org/W2118850452","https://openalex.org/W2183341477","https://openalex.org/W2293049663","https://openalex.org/W2293512268","https://openalex.org/W2462831000","https://openalex.org/W2476548250","https://openalex.org/W2502312327","https://openalex.org/W2518172956","https://openalex.org/W2518406046","https://openalex.org/W2747744257","https://openalex.org/W2810518847","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2963035245","https://openalex.org/W2964121592","https://openalex.org/W2970006822","https://openalex.org/W2972497784","https://openalex.org/W2997669187","https://openalex.org/W3095936335","https://openalex.org/W3098557217","https://openalex.org/W3152148971","https://openalex.org/W3154451338","https://openalex.org/W3158484908","https://openalex.org/W3162512456","https://openalex.org/W3197646400","https://openalex.org/W4288284643","https://openalex.org/W4301206121","https://openalex.org/W4301581299","https://openalex.org/W4321062136","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6686164453","https://openalex.org/W6718683173","https://openalex.org/W6724804524","https://openalex.org/W6731370813","https://openalex.org/W6765721730","https://openalex.org/W6765779288","https://openalex.org/W6767111847","https://openalex.org/W6773820404","https://openalex.org/W6794794944"],"related_works":["https://openalex.org/W4321441197","https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"is":[3,62,87],"the":[4,11,24,48,51,76,79,96,113,130,133,138],"speech-to-speech":[5],"(STS)":[6],"synthesis":[7],"process":[8],"that":[9],"converts":[10],"vocal":[12],"identity":[13],"of":[14,78,132],"a":[15,19,43,90,98,103,122],"source":[16],"speaker":[17,21],"to":[18,74],"target":[20],"by":[22],"keeping":[23],"linguistic":[25],"content":[26],"unaltered.":[27],"In":[28],"recent":[29],"years,":[30],"VC":[31,54,73],"research":[32],"has":[33],"been":[34],"explored":[35],"using":[36],"generative":[37],"adversarial":[38],"network":[39],"(GAN)":[40],"models.":[41],"However,":[42],"substantial":[44],"difference":[45],"exists":[46],"between":[47],"real":[49],"and":[50,102,121],"state-of-the-art":[52],"(SOTA)":[53],"model-generated":[55],"speech":[56,81,124],"samples":[57],"as":[58,60],"far":[59],"naturalness":[61,77],"concerned.":[63],"This":[64],"work":[65],"proposes":[66],"an":[67],"improved":[68,84],"GAN":[69,85],"model":[70,86,115,136],"for":[71],"non-parallel":[72],"enhance":[75],"generated":[80],"samples.":[82],"The":[83,126],"integrated":[88],"with":[89],"region-wise":[91],"positional":[92],"normalization":[93],"technique":[94],"in":[95],"generator,":[97],"relativistic":[99],"mechanism-based":[100],"discriminator,":[101],"Fr\u00e9chet":[104],"inception":[105],"distance":[106],"(FID)":[107],"based":[108],"loss":[109],"function.":[110],"We":[111],"tested":[112],"proposed":[114,134],"on":[116],"VCC":[117],"2018,":[118],"CMU":[119],"Arctic,":[120],"dysarthric":[123],"dataset.":[125],"experimental":[127],"results":[128],"revealed":[129],"superiority":[131],"FID-RPRGAN-VC":[135],"over":[137],"SOTA":[139],"MaskCycleGAN-VC":[140],"model.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}