{"ID":2827558,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16518","arxiv_id":"2512.16518","title":"Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning","abstract":"Silent speech interface (SSI) enables hands-free input without audible vocalization, but most SSI systems do not verify speaker identity. We present HEar-ID, which uses consumer active noise-canceling earbuds to capture low-frequency \"whisper\" audio and high-frequency ultrasonic reflections. Features from both streams pass through a shared encoder, producing embeddings that feed a contrastive branch for user authentication and an SSI head for silent spelling recognition. This design supports decoding of 50 words while reliably rejecting impostors, all on commodity earbuds with a single model. Experiments demonstrate that HEar-ID achieves strong spelling accuracy and robust authentication.","short_abstract":"Silent speech interface (SSI) enables hands-free input without audible vocalization, but most SSI systems do not verify speaker identity. We present HEar-ID, which uses consumer active noise-canceling earbuds to capture low-frequency \"whisper\" audio and high-frequency ultrasonic reflections. Features from both streams...","url_abs":"https://arxiv.org/abs/2512.16518","url_pdf":"https://arxiv.org/pdf/2512.16518v1","authors":"[\"Xuefu Dong\",\"Liqiang Xu\",\"Lixing He\",\"Zengyi Han\",\"Ken Christofferson\",\"Yifei Chen\",\"Akihito Taya\",\"Yuuki Nishiyama\",\"Kaoru Sezaki\"]","published":"2025-12-18T13:30:11Z","proceeding":"cs.HC","tasks":"[\"cs.HC\",\"eess.AS\"]","methods":"[]","has_code":false}