mlsanityData to 7 Oct 2026

Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems

arXiv 2409.01813 ↗First posted 3 Sep 2024eess.AS cs.LG cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

In this study, we investigate whether noise-augmented training can concurrently improve adversarial robustness in automatic speech recognition (ASR) systems. We conduct a comparative analysis of the adversarial robustness of four different ASR architectures, each trained under three different augmentation conditions: (1) background noise, speed variations, and reverberations; (2) speed variations only; (3) no data augmentation. We then evaluate the robustness of all resulting models against attacks with white-box or black-box adversarial examples. Our results demonstrate that noise augmentation not only enhances model performance on noisy speech but also improves the model's robustness to adversarial attacks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 3 Sep 2024.

Builds on

36 of 51 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  7. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  10. 2015Listen, Attend and Spellcited by 542
  11. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  12. 2018SDR - half-baked or well done?cited by 420
24 more
  1. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  2. 2015Attention-Based Models for Speech Recognitioncited by 400
  3. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  4. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  5. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  6. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  7. 2023End-to-End Speech Recognition: A Surveycited by 127
  8. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  9. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
  10. 2019Adversarial Examples Are a Natural Consequence of Test Error in Noisecited by 114
  11. 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
  12. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  13. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 83
  14. 2019The Limitations of Adversarial Training and the Blind-Spot Attackcited by 63
  15. 2019SpecAugment on Large Scale Datasetscited by 60
  16. 2018Did you hear that? Adversarial Examples Against Automatic Speech Recognitioncited by 48
  17. 2019Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systemscited by 37
  18. 2019Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?cited by 25
  19. 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
  20. 2022Recent improvements of ASR models in the face of adversarial attackscited by 13
  21. 2022There is more than one kind of robustness: Fooling Whisper with adversarial examplescited by 11
  22. 2019Improving Deep Speech Denoising by Noisy2Noisy Signal Mappingcited by 6
  23. 2021Robustifying automatic speech recognition by extracting slowly varying featurescited by 3
  24. 2023DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distributioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attackscited by 0