Work

On-Device Speech Filtering for Privacy-Preserving Acoustic Activity Recognition

Year: 2024

Type: conference-paper

Abstract: Acoustic sensing has become increasingly prevalent for mobile and ambient devices for applications such as human activity recognition, health monitoring, and environmental sensing. These approaches develop audio featurization techniques to enable machine learning-based inferences while offering privacy by preventing speech reconstruction. However, recent work [2] has shown that such methods are still vulnerable to speech content recovery when fine-tuned automatic speech recognition (ASR) models are applied. Here, we demonstrate the broad applicability of on-device speech filtering using a detect-and-remove method for acoustic sensing tasks, significantly reducing privacy risks in revealing speech content. Additionally, we introduce an interactive tool to experiment with audio featurization methods, aiding the development of privacy-preserving applications.

Source: Proceedings of the 28th Annual International Conference on Mobile Computing And Networking

DOI: 10.1145/3636534.3698865

Authors: Haozhe Zhou, Sudershan Boovaraghavan, Mayank Goel, Yuvraj Agarwal

Institution: Carnegie Mellon University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Award: SaTC: CORE: Medium: End-to-End Support for Privacy in the Internet -of-things