Real-Time Neural Voice Camouflage

12/14/2021
by   Mia Chiquier, et al.
0

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these systems without inconveniencing the conversation between people in the room. Standard adversarial attacks are not effective in real-time streaming situations because the characteristics of the signal will have changed by the time the attack is executed. We introduce predictive attacks, which achieve real-time performance by forecasting the attack that will be the most effective in the future. Under real-time constraints, our method jams the established speech recognition system DeepSpeech 4.17x more than baselines as measured through word error rate, and 7.27x more as measured through character error rate. We furthermore demonstrate our approach is practically effective in realistic environments over physical distances.

READ FULL TEXT

page 1

page 4

page 9

research
03/31/2021

Adversarial Attacks and Defenses for Speech Recognition Systems

The ubiquitous presence of machine learning systems in our lives necessi...
research
02/17/2023

From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition

Consumer speech recognition systems do not work as well for many people ...
research
05/09/2023

VSMask: Defending Against Voice Synthesis Attack via Real-Time Predictive Perturbation

Deep learning based voice synthesis technology generates artificial huma...
research
01/10/2023

Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition

While speech recognition Word Error Rate (WER) has reached human parity ...
research
01/24/2018

CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition

ASR (automatic speech recognition) systems like Siri, Alexa, Google Voic...
research
09/20/2023

AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition

Automatic Speech Recognition systems have been shown to be vulnerable to...
research
02/23/2023

Can Voice Assistants Be Microaggressors? Cross-Race Psychological Responses to Failures of Automatic Speech Recognition

Language technologies have a racial bias, committing greater errors for ...

Please sign up or login with your details

Forgot password? Click here to reset