Universal Semantic Disentangled Privacy-preserving Speech Representation Learning
Reviewed by Pithpith:BTUKWIDZopen to challenge →
read the original abstract
The use of audio recordings of human speech to train LLMs poses privacy concerns due to these models' potential to generate outputs that closely resemble artifacts in the training data. In this study, we propose a speaker privacy-preserving representation learning method through the Universal Speech Codec (USC), a computationally efficient encoder-decoder model that disentangles speech into: (i) privacy-preserving semantically rich representations, capturing content and speech paralinguistics, and (ii) residual acoustic and speaker representations that enables high-fidelity reconstruction. Extensive evaluations presented show that USC's semantic representation preserves content, prosody, and sentiment, while removing potentially identifiable speaker attributes. Combining both representations, USC achieves state-of-the-art speech reconstruction. Additionally, we introduce an evaluation methodology for measuring privacy-preserving properties, aligning with perceptual tests. We compare USC against other codecs in the literature and demonstrate its effectiveness on privacy-preserving representation learning, illustrating the trade-offs of speaker anonymization, paralinguistics retention and content preservation in the learned semantic representations. Audio samples are shared in https://www.amazon.science/usc-samples.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization
InfoShield uses TimeAwareMINE to minimize mutual information between speech representations and sensitive attributes, cutting gender inference from 92.6% to 55.5% and age inference from 55.7% to 30.3% while dropping d...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.