{"id":"https://openalex.org/W7221031920","doi":"https://doi.org/10.48550/arxiv.2610.08276","title":"Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance","display_name":"Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7221031920","doi":"https://doi.org/10.48550/arxiv.2610.08276"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.08276","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08276","pdf_url":"https://arxiv.org/pdf/2610.08276","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.08276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157987811","display_name":"Xiang Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi, Xiang","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157948550","display_name":"Han Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Han","raw_affiliation_strings":["Duke Kunshan University Xiaomi Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University Xiaomi Corporation","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157960481","display_name":"Ming F. Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":["Duke Kunshan University Xiaomi Corporation School of Artificial Intelligence ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University Xiaomi Corporation School of Artificial Intelligence ,","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102018159","display_name":"Xiaoxiao Miao","orcid":"https://orcid.org/0000-0002-6645-6524","observed_orcids":["https://orcid.org/0000-0002-6645-6524"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao, Xiaoxiao","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9940999746322632,"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":0.9940999746322632,"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":0.0034000000450760126,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/voice-anonymization","display_name":"voice anonymization","score":0.984000027179718},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.875},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.9259999990463257},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"emotion recognition","score":0.6850000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7746999859809875},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7669000029563904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.675599992275238},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5940999984741211},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49810001254081726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48330000042915344},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.3208000063896179},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.08276","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08276","pdf_url":"https://arxiv.org/pdf/2610.08276","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.08276","doi":"https://doi.org/10.48550/arxiv.2610.08276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.08276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.08276","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08276","pdf_url":"https://arxiv.org/pdf/2610.08276","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221031920.pdf","grobid_xml":"https://content.openalex.org/works/W7221031920.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2972848589","https://openalex.org/W3021040286","https://openalex.org/W4281736089","https://openalex.org/W4284706634","https://openalex.org/W4385749691","https://openalex.org/W4404569231","https://openalex.org/W6967206274","https://openalex.org/W7158537106"],"related_works":["https://openalex.org/W6996685145","https://openalex.org/W4403309913","https://openalex.org/W7063008734","https://openalex.org/W4385822306","https://openalex.org/W7168254587","https://openalex.org/W4396611751","https://openalex.org/W7204557545","https://openalex.org/W7126099789","https://openalex.org/W3166661385","https://openalex.org/W4409683700"],"abstract_inverted_index":{"Voice":[0],"anonymization":[1,25],"aims":[2],"to":[3,49,67],"conceal":[4],"speaker":[5,47,115],"identity":[6],"while":[7,54,83,117],"preserving":[8,55],"linguistic":[9,56],"and":[10,77,96,123],"paralinguistic":[11],"information,":[12],"yet":[13],"many":[14],"existing":[15],"methods":[16],"require":[17],"dedicated":[18],"training.":[19],"We":[20],"propose":[21],"a":[22,44],"training-free,":[23],"two-stage":[24,112],"method":[26,91,113],"for":[27],"pretrained":[28,101],"flow-matching":[29],"voice":[30],"conversion":[31],"systems.":[32],"In":[33,58],"the":[34,37,59,62,69,74,78,111],"condition-construction":[35],"stage,":[36,61],"source":[38,63],"content":[39,85],"representation":[40],"is":[41,65,81,87],"regenerated":[42],"under":[43],"randomly":[45],"selected":[46],"context":[48],"reduce":[50],"residual":[51],"source-speaker":[52],"information":[53],"content.":[57],"speech-generation":[60],"speech":[64],"used":[66],"identify":[68],"generation":[70],"direction":[71],"associated":[72],"with":[73],"original":[75],"speaker,":[76],"source-aligned":[79],"component":[80],"suppressed":[82],"useful":[84],"guidance":[86],"retained.":[88],"The":[89],"proposed":[90],"modifies":[92],"only":[93],"inference-time":[94],"conditioning":[95],"guidance,":[97],"without":[98],"updating":[99],"any":[100],"parameters.":[102],"Experiments":[103],"on":[104],"VoicePrivacy":[105],"2026":[106],"Track":[107],"1":[108],"show":[109],"that":[110],"improves":[114],"privacy":[116],"maintaining":[118],"competitive":[119],"word":[120],"error":[121],"rate":[122],"emotion":[124],"recognition":[125],"performance.":[126]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}
