Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning. (arXiv:2308.04960v1 [cs.SD])

Privacy preservation has long been a concern in smart acoustic monitoring
systems, where speech can be passively recorded along with a target signal in
the system's operating environment. In this study, we propose the integration
of two commonly used approaches in privacy preservation: source separation and
adversarial representation learning. The proposed system learns the latent
representation of audio recordings such that it prevents differentiating
between speech and non-speech recordings. Initially, the source separation
network filters out some of the privacy-sensitive …

acoustic adversarial audio environment integration monitoring preservation privacy representation signal smart speech study system systems target