HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment

TL;DR

HighRateMOS is a novel speech quality assessment model that explicitly incorporates sampling rate information, leading to more accurate and robust predictions across different audio sampling rates.

Contribution

It introduces the first sampling-rate-aware MOS model that combines multiple features and embeddings to improve speech quality prediction robustness.

Findings

Ranked first in five out of eight metrics in AudioMOS 2025 Track3.

Model demonstrates improved robustness across varying sampling rates.

Explicit sampling rate modeling enhances prediction accuracy.

Abstract

Modern speech quality prediction models are trained on audio data resampled to a specific sampling rate. When faced with higher-rate audio at test time, these models can produce biased scores. We introduce HighRateMOS, the first non-intrusive mean opinion score (MOS) model that explicitly considers sampling rate. HighRateMOS ensembles three model variants that exploit the following information: (i) a learnable embedding of speech sampling rate, (ii) Wav2vec 2.0 self-supervised embeddings, (iii) multi-scale CNN spectral features, and (iv) MFCC features. In AudioMOS 2025 Track3, HighRateMOS ranked first in five out of eight metrics. Our experiments confirm that modeling the sampling rate directly leads to more robust and sampling-rate-agnostic speech quality predictions.