Diffusion-based spectral super-resolution of third octave acoustic sensor data: is privacy at risk ?
Résumé
Third octave spectral recording of acoustic sensor data is an effective way of measuring the environment. While there is strong evidence that slow (1s frame, 1 Hz rate) and fast (125ms frame, 8Hz rate) versions lead by-design to unintelligible speech if reconstructed, the advent of high quality reconstruction methods based on diffusion may pose a threat, as those approaches can embed a significant amount of a priori knowledge when learned over extensive speech datasets.
This paper aims to assess this risk at three levels of attacks with a growing level of a priori knowledge considered at the learning of the diffusion model, a) none, b) multi-speaker data excluding the target speaker and c) target speaker. Without any prior regarding the speech profile of the speaker (levels a and b), our results suggest a rather low risk as the worderror-rate both for humans and automatic recognition remains higher than 89%.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |