Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908720078782464 |
|---|---|
| author | Dong, Xuefu Xu, Liqiang He, Lixing Han, Zengyi Christofferson, Ken Chen, Yifei Taya, Akihito Nishiyama, Yuuki Sezaki, Kaoru |
| author_facet | Dong, Xuefu Xu, Liqiang He, Lixing Han, Zengyi Christofferson, Ken Chen, Yifei Taya, Akihito Nishiyama, Yuuki Sezaki, Kaoru |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_16518 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning Dong, Xuefu Xu, Liqiang He, Lixing Han, Zengyi Christofferson, Ken Chen, Yifei Taya, Akihito Nishiyama, Yuuki Sezaki, Kaoru Human-Computer Interaction Audio and Speech Processing 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. |
| title | Poster: Recognizing Hidden-in-the-Ear Private Key for Reliable Silent Speech Interface Using Multi-Task Learning |
| topic | Human-Computer Interaction Audio and Speech Processing |
| url | https://arxiv.org/abs/2512.16518 |