2024/01/01 by Dongqi Cai, Cai, Dongqi
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Audio and Speech Processing (eess.AS) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2401.11983
openalex publication_date 2024/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Speech is a common input method for mobile embedded devices, but cloud-based speech recognition systems pose privacy risks. Disentanglement-based encoders, designed to safeguard user privacy by filtering sensitive information from speech signals, unfortunately require substantial memory and computational resources, which limits their use in less powerful devices. To overcome this, we introduce a novel system, XXX, optimized for such devices. XXX is built on the insight that speech understanding primarily relies on understanding the entire utterance's long-term dependencies, while privacy concerns are often linked to short-term details. Therefore, XXX focuses on selectively masking these short-term elements, preserving the quality of long-term speech understanding. The core of XXX is an innovative differential mask generator, grounded in interpretable learning, which fine-tunes the masking process. We tested XXX on the STM32H7 microcontroller, assessing its performance in various potential attack scenarios. The results show that XXX maintains speech understanding accuracy and privacy at levels comparable to existing encoders, but with a significant improvement in efficiency, achieving up to 53.3× faster processing and a 134.1× smaller memory footprint.