AntiFake: Using Adversarial Audio to Prevent Unauthorized Speech Synthesis.

Zhiyuan Yu Shixuan Zhai Ning Zhang

Published in: CCS (2023)

Keyphrases

speech synthesis
prosodic features
text to speech
speech recognition
vocal tract
speaker identification
word processing

speech corpus
multimedia
sensitive information
multi agent
computer vision
visual information
neural network

hidden markov models
pattern recognition
multimedia content
audio visual
automatic speech recognition
multimedia information

signal processing
data protection
secret information
feature extraction
audio recordings
machine learning