Home / Publications / E-library page
Only AES members and Institutional Journal Subscribers can download
An automatic speech recognition (ASR) system based on a deep neural network is vulnerable to attack by an adversarial example, especially if the command-dependent ASR fails. A defense method against adversarial examples is proposed to improve the robustness and security of the ASR system. An algorithm of devastation and detection on adversarial examples that can attack current advanced ASR systems is proposed. An advanced text-dependent and command-dependent ASR system is chosen as the target, generating adversarial examples by an optimization-based attack on text-dependent ASR and the genetic-algorithm--based algorithm on command-dependent ASR. The method is based on input transformation of adversarial examples. Different random intensities and kinds of noise are added to adversarial examples to devastate the perturbation previously added to normal examples. Experimental results show that the method performs well. For the devastation of examples, the original speech similarity after adding noise can reach 99.68%, the similarity of adversarial examples can reach zero, and the detection rate of adversarial examples can reach 94%.
Author (s): Dong, Mingyu; Yan, Diqun; Gong, Yongkang
Affiliation:
College of Information Science and Engineering, Ningbo University, Ningbo Zhejiang, China
(See document for exact affiliation information.)
Publication Date:
2023-01-06
Import into BibTeX
Permalink: https://aes2.org/publications/elibrary-page/?id=22029
(913KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
Dong, Mingyu; Yan, Diqun; Gong, Yongkang; 2023; Adversarial Example Devastation and Detection on Speech Recognition System by Adding Random Noise [PDF]; College of Information Science and Engineering, Ningbo University, Ningbo Zhejiang, China; Paper ; Available from: https://aes2.org/publications/elibrary-page/?id=22029
Dong, Mingyu; Yan, Diqun; Gong, Yongkang; Adversarial Example Devastation and Detection on Speech Recognition System by Adding Random Noise [PDF]; College of Information Science and Engineering, Ningbo University, Ningbo Zhejiang, China; Paper ; 2023 Available: https://aes2.org/publications/elibrary-page/?id=22029
@article{dong2023adversarial,
author={dong mingyu and yan diqun and gong yongkang},
journal={journal of the audio engineering society},
title={adversarial example devastation and detection on speech recognition system by adding random noise},
year={2023},
volume={71},
issue={1/2},
pages={34-44},
month={january},}