Hiding speaker's sex in speech using zero-evidence speaker representation in an analysis/synthesis pipeline

2022/11/29 by ‪Paul-Gauthier Noé‬, Noé, Paul-Gauthier, Xiaoxiao Miao +9 · 2 citations
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2211.16065

openalex publication_date 2022/11/29 · openalex created_date 2022/12/11 · openalex updated_date 2026/07/28

Abstract

The use of modern vocoders in an analysis/synthesis pipeline allows us to investigate high-quality voice conversion that can be used for privacy purposes. Here, we propose to transform the speaker embedding and the pitch in order to hide the sex of the speaker. ECAPA-TDNN-based speaker representation fed into a HiFiGAN vocoder is protected using a neural-discriminant analysis approach, which is consistent with the zero-evidence concept of privacy. This approach significantly reduces the information in speech related to the speaker's sex while preserving speech content and some consistency in the resulting protected voices.

Cited by

• The distribution of calibrated likelihood functions on the probability-likelihood Aitchison simplex
• Reference-free Adversarial Sex Obfuscation in Speech

Related

• Generating gender-ambiguous voices for privacy-preserving speech recognition
• Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation
• Protecting gender and identity with disentangled speech representations
• Differentially Private Adversarial Auto-Encoder to Protect Gender in Voice Biometrics
• Reference-free Adversarial Sex Obfuscation in Speech