Guardado en:
Detalles Bibliográficos
Autores principales: Ren, Wenze, Lin, Yi-Cheng, Huang, Wen-Chin, Cooper, Erica, Zezario, Ryandhimas E., Wang, Hsin-Min, Lee, Hung-yi, Tsao, Yu
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.10723
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911517411115008
author Ren, Wenze
Lin, Yi-Cheng
Huang, Wen-Chin
Cooper, Erica
Zezario, Ryandhimas E.
Wang, Hsin-Min
Lee, Hung-yi
Tsao, Yu
author_facet Ren, Wenze
Lin, Yi-Cheng
Huang, Wen-Chin
Cooper, Erica
Zezario, Ryandhimas E.
Wang, Hsin-Min
Lee, Hung-yi
Tsao, Yu
contents The Mean Opinion Score (MOS) serves as the standard metric for speech quality assessment, yet biases in human annotations remain underexplored. We conduct the first systematic analysis of gender bias in MOS, revealing that male listeners consistently assign higher scores than female listeners--a gap that is most pronounced in low-quality speech and gradually diminishes as quality improves. This quality-dependent structure proves difficult to eliminate through simple calibration. We further demonstrate that automated MOS models trained on aggregated labels exhibit predictions skewed toward male standards of perception. To address this, we propose a gender-aware model that learns gender-specific scoring patterns through abstracting binary group embeddings, thereby improving overall and gender-specific prediction accuracy. This study establishes that gender bias in MOS constitutes a systematic, learnable pattern demanding attention in equitable speech evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10723
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MOS-Bias: From Hidden Gender Bias to Gender-Aware Speech Quality Assessment
Ren, Wenze
Lin, Yi-Cheng
Huang, Wen-Chin
Cooper, Erica
Zezario, Ryandhimas E.
Wang, Hsin-Min
Lee, Hung-yi
Tsao, Yu
Audio and Speech Processing
The Mean Opinion Score (MOS) serves as the standard metric for speech quality assessment, yet biases in human annotations remain underexplored. We conduct the first systematic analysis of gender bias in MOS, revealing that male listeners consistently assign higher scores than female listeners--a gap that is most pronounced in low-quality speech and gradually diminishes as quality improves. This quality-dependent structure proves difficult to eliminate through simple calibration. We further demonstrate that automated MOS models trained on aggregated labels exhibit predictions skewed toward male standards of perception. To address this, we propose a gender-aware model that learns gender-specific scoring patterns through abstracting binary group embeddings, thereby improving overall and gender-specific prediction accuracy. This study establishes that gender bias in MOS constitutes a systematic, learnable pattern demanding attention in equitable speech evaluation.
title MOS-Bias: From Hidden Gender Bias to Gender-Aware Speech Quality Assessment
topic Audio and Speech Processing
url https://arxiv.org/abs/2603.10723