{"id":"https://openalex.org/W7135197581","doi":"https://doi.org/10.1109/iccp68926.2025.11427135","title":"Speaker Anonymization via GAN-driven Artificial Embeddings and Prosody Transfer","display_name":"Speaker Anonymization via GAN-driven Artificial Embeddings and Prosody Transfer","publication_year":2025,"publication_date":"2025-10-16","ids":{"openalex":"https://openalex.org/W7135197581","doi":"https://doi.org/10.1109/iccp68926.2025.11427135"},"language":null,"primary_location":{"id":"doi:10.1109/iccp68926.2025.11427135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp68926.2025.11427135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Intelligent Computer Communication and Processing (ICCP)","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/A5129016676","display_name":"Dumitru-Cosmin Melinte","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Dumitru-Cosmin Melinte","raw_affiliation_strings":["Technical University of Cluj-Napoca,Telecommunications Department,Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Telecommunications Department,Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121807595","display_name":"Mircea Giurgiu","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Giurgiu","raw_affiliation_strings":["Technical University of Cluj-Napoca,Telecommunications Department,Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Telecommunications Department,Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5129016676"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88332384,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.878000020980835,"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":0.878000020980835,"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/T10863","display_name":"Voice and Speech Disorders","score":0.013000000268220901,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.012000000104308128,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.49970000982284546},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28119999170303345},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2551000118255615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.24469999969005585}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254999995231628},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4474000036716461},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.24469999969005585},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.243599995970726}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccp68926.2025.11427135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccp68926.2025.11427135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Intelligent Computer Communication and Processing (ICCP)","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":10,"referenced_works":["https://openalex.org/W3024768724","https://openalex.org/W3043999252","https://openalex.org/W3197790422","https://openalex.org/W3216758611","https://openalex.org/W4296069300","https://openalex.org/W4319862433","https://openalex.org/W4372260248","https://openalex.org/W4403310498","https://openalex.org/W4403310896","https://openalex.org/W4412624422"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,29,41,65,92,154],"novel":[4],"approach":[5],"for":[6,78],"speaker":[7,54,75],"anonymization":[8],"based":[9],"on":[10],"cascaded":[11],"speech-to-text":[12],"(STT)":[13],"and":[14,39,74,94,117,134,149],"text-to-speech":[15],"(TTS)":[16],"Deep":[17],"Neural":[18],"Networks":[19],"(DNNs),":[20],"where":[21],"the":[22,36,47,79,86,99,105,129,132,138],"multi-speaker":[23],"TTS":[24,80,135],"component":[25,81],"is":[26,101],"driven":[27],"by":[28,40],"Generative":[30],"Adversarial":[31],"Network":[32],"(GAN)":[33],"to":[34,45,60,128,153],"anonymize":[35],"speakers\u2019":[37],"identity":[38],"prosody":[42,72,100],"transfer":[43],"module":[44],"preserve":[46],"original":[48,116],"prosody.":[49],"The":[50,71,108],"GAN":[51],"creates":[52],"artificial":[53],"embeddings":[55,87],"that":[56],"do":[57],"not":[58],"correspond":[59],"any":[61],"real":[62],"identity,":[63],"enabling":[64],"high":[66],"diversity":[67],"of":[68,131,145,157],"synthesized":[69,106],"voices.":[70],"preservation":[73],"embedding":[76],"generation":[77],"are":[82,88],"clearly":[83],"distinct":[84],"approaches:":[85],"progressively":[89],"generated":[90],"from":[91],"low":[93,112],"compact":[95],"latent":[96],"space,":[97],"while":[98],"directly":[102],"cloned":[103],"onto":[104],"speech.":[107],"experimental":[109],"results":[110],"show":[111],"cosine":[113],"similarity":[114],"between":[115],"anonymized":[118],"embeddings,":[119],"with":[120],"some":[121],"minor":[122],"degradation":[123],"in":[124],"linguistic":[125],"fidelity":[126],"due":[127],"performance":[130],"STT":[133],"components.":[136],"Additionally,":[137],"developed":[139],"visual":[140],"interface":[141],"supports":[142],"comparative":[143],"analysis":[144],"audio":[146],"features":[147],"before":[148],"after":[150],"anonymization,":[151],"contributing":[152],"qualitative":[155],"assessment":[156],"system":[158],"performance.":[159]},"counts_by_year":[],"updated_date":"2026-03-15T07:15:06.534987","created_date":"2026-03-14T00:00:00"}