{"ID":2886862,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02295","arxiv_id":"2508.02295","title":"Reference-free Adversarial Sex Obfuscation in Speech","abstract":"Sex conversion in speech involves privacy risks from data collection and often leaves residual sex-specific cues in outputs, even when target speaker references are unavailable. We introduce RASO for Reference-free Adversarial Sex Obfuscation. Innovations include a sex-conditional adversarial learning framework to disentangle linguistic content from sex-related acoustic markers and explicit regularisation to align fundamental frequency distributions and formant trajectories with sex-neutral characteristics learned from sex-balanced training data. RASO preserves linguistic content and, even when assessed under a semi-informed attack model, it significantly outperforms a competing approach to sex obfuscation.","short_abstract":"Sex conversion in speech involves privacy risks from data collection and often leaves residual sex-specific cues in outputs, even when target speaker references are unavailable. We introduce RASO for Reference-free Adversarial Sex Obfuscation. Innovations include a sex-conditional adversarial learning framework to dise...","url_abs":"https://arxiv.org/abs/2508.02295","url_pdf":"https://arxiv.org/pdf/2508.02295v1","authors":"[\"Yangyang Qu\",\"Michele Panariello\",\"Massimiliano Todisco\",\"Nicholas Evans\"]","published":"2025-08-04T11:04:23Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[]","has_code":false}