Abstract

ABSTRACT

This document describes an acoustic camouflage system that provides localized acoustic privacy during voice-based interactions with a computing device, such as a laptop computer, smart phone, mobile device, tablet, or wearable computing device, etc. To provide sound masking and speech obfuscation, the computing device generates a synthetic masking signal that blends an inverse audio wave of the user's speech into existing ambient or environmental noise. To synchronize this noise suppression, the computing device uses sensed data of the user, such as video data of lip movements of the user, to predict speech before it is vocalized. The computing device may dynamically activate active noise cancellation when it detects the user is sharing sensitive information, such as speaking a password or in response to an on-screen keyboard display prompting for a password. To optimize accuracy and reduce the energy needed to muffle the user's voice, the device may also create a locally stored, personalized acoustic profile of the user's unique speech patterns.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS