{"id":"https://openalex.org/W4415583943","doi":"https://doi.org/10.1186/s13636-025-00422-5","title":"ICRCycleGAN-VC: a robust one-to-one voice conversion method based on CycleGAN and inception-ResNet blocks","display_name":"ICRCycleGAN-VC: a robust one-to-one voice conversion method based on CycleGAN and inception-ResNet blocks","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4415583943","doi":"https://doi.org/10.1186/s13636-025-00422-5"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00422-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00422-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00422-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00422-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120148894","display_name":"Nayereh Seyed Afiuny","orcid":null},"institutions":[{"id":"https://openalex.org/I184468904","display_name":"University of Qom","ror":"https://ror.org/03ddeer04","country_code":"IR","type":"education","lineage":["https://openalex.org/I184468904"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Nayereh Seyed Afiuny","raw_affiliation_strings":["Computer Engineering Department, University of Qom, Qom, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, University of Qom, Qom, Iran","institution_ids":["https://openalex.org/I184468904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033018744","display_name":"Amir Lakizadeh","orcid":"https://orcid.org/0000-0001-9870-3676"},"institutions":[{"id":"https://openalex.org/I184468904","display_name":"University of Qom","ror":"https://ror.org/03ddeer04","country_code":"IR","type":"education","lineage":["https://openalex.org/I184468904"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Amir Lakizadeh","raw_affiliation_strings":["Computer Engineering Department, University of Qom, Qom, Iran"],"raw_orcid":"https://orcid.org/0000-0001-9870-3676","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, University of Qom, Qom, Iran","institution_ids":["https://openalex.org/I184468904"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120148894"],"corresponding_institution_ids":["https://openalex.org/I184468904"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.0776,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90614604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2025","issue":"1","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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9983999729156494,"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/robustness","display_name":"Robustness (evolution)","score":0.7145000100135803},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6312999725341797},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5479000210762024},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45879998803138733},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44830000400543213},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4377000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8781999945640564},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7145000100135803},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6312999725341797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5598000288009644},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5479000210762024},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45879998803138733},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44830000400543213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41370001435279846},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00422-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00422-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00422-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0b6322f310b54eb4a1936542ec9a981f","is_oa":true,"landing_page_url":"https://doaj.org/article/0b6322f310b54eb4a1936542ec9a981f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00422-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00422-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00422-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415583943.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W1999061088","https://openalex.org/W2022125261","https://openalex.org/W2056852181","https://openalex.org/W2057609679","https://openalex.org/W2105160541","https://openalex.org/W2120197225","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2128123288","https://openalex.org/W2156142001","https://openalex.org/W2247645229","https://openalex.org/W2567070169","https://openalex.org/W2605287558","https://openalex.org/W2739735615","https://openalex.org/W2747744257","https://openalex.org/W2784823820","https://openalex.org/W2797877891","https://openalex.org/W2902070858","https://openalex.org/W2929315483","https://openalex.org/W2936173958","https://openalex.org/W2937579788","https://openalex.org/W2949496494","https://openalex.org/W2963341956","https://openalex.org/W2963420272","https://openalex.org/W2964069186","https://openalex.org/W2964350391","https://openalex.org/W2965685620","https://openalex.org/W2970006822","https://openalex.org/W3012498027","https://openalex.org/W3015959238","https://openalex.org/W3034089333","https://openalex.org/W3094444047","https://openalex.org/W3098557217","https://openalex.org/W3113603766","https://openalex.org/W3162512456","https://openalex.org/W3168719651","https://openalex.org/W3176939825","https://openalex.org/W3204602440","https://openalex.org/W4224295627","https://openalex.org/W4245885054","https://openalex.org/W4288079962","https://openalex.org/W4311000453","https://openalex.org/W4321277041","https://openalex.org/W4322629454","https://openalex.org/W4323339216","https://openalex.org/W4372260053","https://openalex.org/W6910781196"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"conversion":[1,59],"(VC)":[2],"transforms":[3],"a":[4,11,66,141],"source":[5],"speaker\u2019s":[6],"voice":[7,58,146,169],"into":[8,65],"that":[9,61,82],"of":[10,45,96,103,156,163],"target":[12],"speaker":[13],"while":[14],"preserving":[15],"the":[16,88,94,100,153,161],"underlying":[17],"linguistic":[18,97],"content.":[19],"However,":[20],"existing":[21],"methods,":[22],"especially":[23],"for":[24],"languages":[25],"with":[26,34],"complex":[27],"phonetic":[28],"structures":[29],"like":[30],"Persian,":[31],"often":[32],"struggle":[33],"issues":[35],"such":[36,134],"as":[37,135],"over-smoothing,":[38],"inadequate":[39],"multi-scale":[40,71],"feature":[41],"extraction,":[42],"and":[43,76,113,125,148],"loss":[44,79],"essential":[46],"acoustic":[47],"details.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"introduce":[53],"ICRCycleGAN-VC,":[54],"an":[55,77],"innovative":[56],"one-to-one":[57],"framework":[60],"integrates":[62],"Inception-ResNet":[63],"modules":[64],"CycleGAN":[67],"architecture.":[68],"By":[69],"leveraging":[70],"convolutional":[72],"filters,":[73],"residual":[74],"connections,":[75],"optimized":[78],"function":[80],"strategy":[81],"eliminates":[83],"second":[84],"adversarial":[85],"losses":[86],"in":[87,122,144,166],"generator,":[89],"our":[90,164],"approach":[91,165],"significantly":[92],"improves":[93],"preservation":[95],"content,":[98],"addressing":[99],"main":[101],"challenge":[102],"ensuring":[104],"accurate":[105],"content":[106],"retention.":[107],"Extensive":[108],"experiments":[109],"on":[110],"both":[111,145],"Persian":[112],"English":[114],"datasets":[115],"demonstrate":[116],"significant":[117],"improvements,":[118],"achieving":[119],"notable":[120],"reductions":[121],"mel-cepstral":[123],"distortion":[124],"root":[126],"mean":[127],"squared":[128],"error":[129],"compared":[130],"to":[131],"baseline":[132],"models":[133],"MaskCycleGAN-VC.":[136],"Furthermore,":[137],"subjective":[138],"evaluations":[139],"reveal":[140],"substantial":[142],"increase":[143],"similarity":[147],"naturalness.":[149],"Ablation":[150],"studies":[151],"highlight":[152],"critical":[154],"contributions":[155],"each":[157],"architectural":[158],"component,":[159],"confirming":[160],"robustness":[162],"advancing":[167],"non-parallel":[168],"conversion.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-28T00:00:00"}