Latent Secret Spin: Keyed Orthogonal Rotations for Blind Speech Watermarking in Anisotropic Latent Spaces

TL;DR

Latent Secret Spin (LSS) is a blind speech watermarking technique using geometric rotations in latent space, offering robustness, perceptual quality, and flexibility without neural network training.

Contribution

LSS introduces a novel geometric approach to speech watermarking in latent spaces that is dataset-agnostic, neural network-free, and resistant to common signal manipulations.

Findings

LSS preserves perceptual quality while embedding watermarks.

LSS is resistant to common signal manipulations.

LSS generalizes across datasets and is flexible in payload size.

Abstract

We introduce Latent Secret Spin (LSS), a blind speech watermarking method based on geometric operations in codec latent space. Based upon orthogonal rotations to principal components, LSS induces imperceptible but detectable covariance signatures according to a pseudo-random watermarking schedule. The scheme generalises across datasets, preserves perceptual quality and, unlike some learned, neural watermarking schemes, it does not require neural network training, is resistant to common signal manipulations and is flexible to payload size. Analyses show that structured latent-space watermarking is a promising and interpretable alternative to existing approaches.