Trade-offs Between Capacity and Robustness in Neural Audio Codecs for Adversarially Robust Speech Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Prescott, Jordan, Lertpetchpun, Thanathai, Narayanan, Shrikanth
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917327905226752
author Prescott, Jordan
Lertpetchpun, Thanathai
Narayanan, Shrikanth
author_facet Prescott, Jordan
Lertpetchpun, Thanathai
Narayanan, Shrikanth
contents Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a discrete bottleneck that can suppress fine-grained signal variations associated with adversarial noise. We examine how the granularity of this bottleneck, controlled by residual vector quantization (RVQ) depth, shapes adversarial robustness. We observe a non-monotonic trade-off under gradient-based attacks: shallow quantization suppresses adversarial perturbations but degrades speech content, while deeper quantization preserves both content and perturbations. Intermediate depths balance these effects and minimize transcription error. We further show that adversarially induced changes in discrete codebook tokens strongly correlate with transcription error. These gains persist under adaptive attacks, where neural codec configurations outperform traditional compression defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09034
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Trade-offs Between Capacity and Robustness in Neural Audio Codecs for Adversarially Robust Speech Recognition
Prescott, Jordan
Lertpetchpun, Thanathai
Narayanan, Shrikanth
Audio and Speech Processing
Sound
Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a discrete bottleneck that can suppress fine-grained signal variations associated with adversarial noise. We examine how the granularity of this bottleneck, controlled by residual vector quantization (RVQ) depth, shapes adversarial robustness. We observe a non-monotonic trade-off under gradient-based attacks: shallow quantization suppresses adversarial perturbations but degrades speech content, while deeper quantization preserves both content and perturbations. Intermediate depths balance these effects and minimize transcription error. We further show that adversarially induced changes in discrete codebook tokens strongly correlate with transcription error. These gains persist under adaptive attacks, where neural codec configurations outperform traditional compression defenses.
title Trade-offs Between Capacity and Robustness in Neural Audio Codecs for Adversarially Robust Speech Recognition
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2603.09034