Audio sample demo

Attacking UTMOS: Probing the Robustness of a Speech Quality Assessment Model

Wen-Chin Huang and Tomoki Toda

Nagoya University, Japan

Static Audio Sample Tables

Browse the same clean references, noise baselines, score-preserving attacks, and quality-preserving attacks for three LibriSpeech utterances.

Noise Baseline

Gaussian noise added in waveform, spectrogram, or EnCodec latent space.

PESQ versus UTMOS scatter plot for random noise perturbation baseline

Score-Preserving Attack

Adversarial samples optimized to keep UTMOS high while lowering perceptual quality.

PESQ versus UTMOS scatter plot for score-preserving attacks

Quality-Preserving Attack

Adversarial samples optimized to lower UTMOS while preserving perceptual quality.

PESQ versus UTMOS scatter plot for quality-preserving attacks