English

RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting

Audio and Speech Processing 2023-09-01 v1 Sound

Abstract

Automatic Mean Opinion Score (MOS) prediction is crucial to evaluate the perceptual quality of the synthetic speech. While recent approaches using pre-trained self-supervised learning (SSL) models have shown promising results, they only partly address the data scarcity issue for the feature extractor. This leaves the data scarcity issue for the decoder unresolved and leading to suboptimal performance. To address this challenge, we propose a retrieval-augmented MOS prediction method, dubbed {\bf RAMP}, to enhance the decoder's ability against the data scarcity issue. A fusing network is also proposed to dynamically adjust the retrieval scope for each instance and the fusion weights based on the predictive confidence. Experimental results show that our proposed method outperforms the existing methods in multiple scenarios.

Keywords

Cite

@article{arxiv.2308.16488,
  title  = {RAMP: Retrieval-Augmented MOS Prediction via Confidence-based Dynamic Weighting},
  author = {Hui Wang and Shiwan Zhao and Xiguang Zheng and Yong Qin},
  journal= {arXiv preprint arXiv:2308.16488},
  year   = {2023}
}

Comments

Accepted by Interspeech 2023, oral

R2 v1 2026-06-28T12:09:02.515Z