HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment
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.
Keywords
Cite
@article{arxiv.2506.21951,
title = {HighRateMOS: Sampling-Rate Aware Modeling for Speech Quality Assessment},
author = {Wenze Ren and Yi-Cheng Lin and Wen-Chin Huang and Ryandhimas E. Zezario and Szu-Wei Fu and Sung-Feng Huang and Erica Cooper and Haibin Wu and Hung-Yu Wei and Hsin-Min Wang and Hung-yi Lee and Yu Tsao},
journal= {arXiv preprint arXiv:2506.21951},
year = {2025}
}
Comments
Under Review, 3 pages + 1 References