Metraipolis › archive › dc_98e83cc64d1c

Removing Speech, Keeping Activities: A Privacy Firewall for Acoustic Sensing in Assisted Living — arXiv:2609.02376

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02376
License (as archived)
CC0-1.0
Archived
2026-10-17T04:44:15.064Z
SHA-256 of the archived text
f812830c3a8fe5293a321ce3fdb5fb17bc2a666079908ff0107f65ba63bedabd
Stable URL of this page
https://metraipolis.com/documento/dc_98e83cc64d1c

How to cite

Removing Speech, Keeping Activities: A Privacy Firewall for Acoustic Sensing in Assisted Living — arXiv:2609.02376 — arXiv (en), https://arxiv.org/abs/2609.02376 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98e83cc64d1c (Metraipolis archive dc_98e83cc64d1c, sha256 f812830c3a8fe5293a321ce3fdb5fb17bc2a666079908ff0107f65ba63bedabd)
BibTeX
@misc{dc98e83cc64d1c,
  title = {Removing Speech, Keeping Activities: A Privacy Firewall for Acoustic Sensing in Assisted Living — arXiv:2609.02376},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02376},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98e83cc64d1c; sha256 f812830c3a8fe5293a321ce3fdb5fb17bc2a666079908ff0107f65ba63bedabd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02376. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Acoustic sensing offers a promising non-intrusive approach for monitoring daily activities of older adults, yet speech privacy concerns remain a critical barrier to real-world deployment. We present a privacy firewall pipeline based on a U-Net encoder-decoder, trained entirely on synthetic data, that removes speech from ambient audio while preserving environmental sounds indicative of daily activities. Activity recognition is performed using VGGish transfer learning with an SVM classifier. Evaluated on the ESC-50 and SINS datasets across multiple speech content levels, the proposed model reduced residual speech to 0% VAD-detectable speech (Silero Voice Activity Detection) under all tested conditions, outperforming Facebook Denoiser (6.55% residual), SepFormer (36.34%) and ConvTasNet (47.21%) on ESC-50 at the 100\% speech level. On ESC-50 at 40% speech level, classification performance recovers to 85% precision and 85% recall after speech removal, compared with 81%/75% before removal and an 84%/83% speech-free baseline. Evaluation on real-world participant home recordings collected with the AudioHive app showed 0% VAD-detectable speech after processing while maintaining 76% precision and recall. The pipeline enables privacy-preserving acoustic sensing without sacrificing activity recognition performance, addressing a key obstacle to the adoption of ambient monitoring in elderly care.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CR).
Categorie arXiv: Sound (cs.SD) ; Cryptography and Security (cs.CR); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.02376 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T04:09:09.372Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).