{"id":"https://openalex.org/W4372346578","doi":"https://doi.org/10.1109/icassp49357.2023.10095069","title":"Voice Conversion Using Feature Specific Loss Function Based Self-Attentive Generative Adversarial Network","display_name":"Voice Conversion Using Feature Specific Loss Function Based Self-Attentive Generative Adversarial Network","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346578","doi":"https://doi.org/10.1109/icassp49357.2023.10095069"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095069","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/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/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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/spectrogram","display_name":"Spectrogram","score":0.803065836429596},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440247535705566},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6756009459495544},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6739678978919983},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6540536284446716},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4681796133518219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45455750823020935},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4388554096221924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4334668815135956},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4251152575016022},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.35201597213745117},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.0775560736656189}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.803065836429596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440247535705566},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6756009459495544},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6739678978919983},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6540536284446716},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4681796133518219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45455750823020935},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4388554096221924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4334668815135956},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4251152575016022},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35201597213745117},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0775560736656189},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095069","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":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1992188827","https://openalex.org/W2120847449","https://openalex.org/W2293049663","https://openalex.org/W2902070858","https://openalex.org/W2913006054","https://openalex.org/W2937579788","https://openalex.org/W2963035245","https://openalex.org/W2963073614","https://openalex.org/W2976736845","https://openalex.org/W2979938509","https://openalex.org/W3095936335","https://openalex.org/W3098557217","https://openalex.org/W3152148971","https://openalex.org/W3158484908","https://openalex.org/W3162512456","https://openalex.org/W3171007011","https://openalex.org/W4221146610","https://openalex.org/W4224928197","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6769216209"],"related_works":["https://openalex.org/W1991209043","https://openalex.org/W2140162372","https://openalex.org/W2147978301","https://openalex.org/W2388243677","https://openalex.org/W1970534163","https://openalex.org/W1522167645","https://openalex.org/W93108289","https://openalex.org/W2567608124","https://openalex.org/W2399240891","https://openalex.org/W4364857608"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"is":[3,79,82,108],"the":[4,8,24,27,32,49,56,94,98,103,140,147,159],"process":[5],"of":[6,11,18,26,35,97,120],"converting":[7],"vocal":[9],"texture":[10],"a":[12,19,45,75,85,115],"source":[13,28],"speaker":[14,21,123],"similar":[15],"to":[16,48,92],"that":[17],"target":[20,99],"without":[22],"altering":[23],"content":[25],"speaker\u2019s":[29],"speech.":[30,70],"With":[31],"ongoing":[33],"developments":[34],"deep":[36],"generative":[37,39],"models,":[38],"adversarial":[40],"networks":[41],"(GANs)":[42],"appeared":[43],"as":[44,114],"better":[46,157],"alternative":[47],"conventional":[50],"statistical":[51],"models":[52],"for":[53],"VC.":[54],"However,":[55],"existing":[57],"VC":[58,77],"model-generated":[59],"speech":[60],"samples":[61],"possess":[62],"substantial":[63],"dissimilarity":[64],"from":[65],"their":[66],"corresponding":[67],"natural":[68],"human":[69],"Therefore,":[71],"in":[72,111,118],"this":[73,112],"work":[74,113],"GAN-based":[76],"model":[78,127,154],"proposed":[80,126,148],"which":[81],"incorporated":[83,110],"with":[84,131],"self-attention":[86],"(SA)":[87],"mechanism":[88],"based":[89],"generator":[90],"network":[91],"obtain":[93],"formant":[95],"distribution":[96],"mel-spectrogram":[100],"efficiently.":[101],"Moreover,":[102],"modulation":[104],"spectra":[105],"distance":[106],"(MSD)":[107],"also":[109],"feature-specific":[116,149],"loss":[117],"terms":[119],"getting":[121],"high":[122],"similarity.":[124],"The":[125],"has":[128],"been":[129],"tested":[130],"CMU":[132],"Arctic":[133],"and":[134,142],"VCC":[135],"2018":[136],"datasets.":[137],"Based":[138],"on":[139],"objective":[141],"subjective":[143],"evaluations,":[144],"we":[145],"observe":[146],"loss-based":[150],"self-attentive":[151],"GAN":[152],"(FLSGAN-VC)":[153],"significantly":[155],"performed":[156],"than":[158],"state-of-the-art":[160],"(SOTA)":[161],"MelGAN-VC":[162],"model.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}