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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Coletta, Emma, Todisco, Massimiliano, Panariello, Michele, Faonio, Antonio, Evans, Nicholas
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911664525279232
author Coletta, Emma
Todisco, Massimiliano
Panariello, Michele
Faonio, Antonio
Evans, Nicholas
author_facet Coletta, Emma
Todisco, Massimiliano
Panariello, Michele
Faonio, Antonio
Evans, Nicholas
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08431
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Latent Secret Spin: Keyed Orthogonal Rotations for Blind Speech Watermarking in Anisotropic Latent Spaces
Coletta, Emma
Todisco, Massimiliano
Panariello, Michele
Faonio, Antonio
Evans, Nicholas
Audio and Speech Processing
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.
title Latent Secret Spin: Keyed Orthogonal Rotations for Blind Speech Watermarking in Anisotropic Latent Spaces
topic Audio and Speech Processing
url https://arxiv.org/abs/2605.08431