# On the robustness of non-intrusive speech quality model by adversarial examples

arXiv: https://arxiv.org/abs/2211.06508 · HTML: https://mlsanity.com/paper/2211.06508/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [Robust Audio Adversarial Example for a Physical Attack](https://mlsanity.com/paper/1810.11793/) (2018)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Non-intrusive speech quality assessment using neural networks](https://mlsanity.com/paper/1903.06908/) (2019)

## Built on by (most cited first, 2 of 2)

- [EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events](https://mlsanity.com/paper/2309.01480/) (2023)
- [How Hackable Is Your Speech Quality Metric? A Corrected Protocol, a Benchmark, and What Patching Buys](https://mlsanity.com/paper/2610.10899/) (2026)

## Abstract (arXiv)

It has been shown recently that deep learning based models are effective on speech quality prediction and could outperform traditional metrics in various perspectives. Although network models have potential to be a surrogate for complex human hearing perception, they may contain instabilities in predictions. This work shows that deep speech quality predictors can be vulnerable to adversarial perturbations, where the prediction can be changed drastically by unnoticeable perturbations as small as -30 dB compared with speech inputs. In addition to exposing the vulnerability of deep speech quality predictors, we further explore and confirm the viability of adversarial training for strengthening robustness of models.