Beyond Neural-on-Neural Approaches to Speaker Gender Protection

Abstract

Recent research has proposed approaches that modify speech to defend against gender inference attacks. The goal of these protection algorithms is to control the availability of information about a speaker's gender, a privacy-sensitive attribute. Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i.e., perturbations are generated and tested with a neural network. In this paper, we propose to go beyond this practice to strengthen the study of gender protection. First, we demonstrate the importance of testing gender inference attacks that are based on speech features historically developed by speech scientists, alongside the conventionally used neural classifiers. Next, we argue that researchers should use speech features to gain insight into how protective modifications change the speech signal. Finally, we point out that gender-protection algorithms should be compared with novel "vocal adversaries", human-executed voice adaptations, in order to improve interpretability and enable before-the-mic protection.

References in corpus (7)

• Explaining and Harnessing Adversarial Examples
• VoxCeleb2: Deep Speaker Recognition
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• Privacy-preserving Voice Analysis via Disentangled Representations
• Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks
• Tubes Among Us: Analog Attack on Automatic Speaker Identification

Cited by in corpus (1)

• Privacy-oriented manipulation of speaker representations