UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

TL;DR

The paper introduces UTMOS, an ensemble-based system for predicting speech quality scores in the VoiceMOS Challenge 2022, achieving top performance on both in-domain and out-of-domain tracks.

Contribution

It presents a novel ensemble approach combining improved SSL-based models and basic machine learning methods for MOS prediction in speech quality assessment.

Findings

Achieved highest scores on multiple metrics in the challenge

Demonstrated effectiveness of ensemble learning and model improvements

Conducted ablation studies confirming method contributions

Abstract

We present the UTokyo-SaruLab mean opinion score (MOS) prediction system submitted to VoiceMOS Challenge 2022. The challenge is to predict the MOS values of speech samples collected from previous Blizzard Challenges and Voice Conversion Challenges for two tracks: a main track for in-domain prediction and an out-of-domain (OOD) track for which there is less labeled data from different listening tests. Our system is based on ensemble learning of strong and weak learners. Strong learners incorporate several improvements to the previous fine-tuning models of self-supervised learning (SSL) models, while weak learners use basic machine-learning methods to predict scores from SSL features. In the Challenge, our system had the highest score on several metrics for both the main and OOD tracks. In addition, we conducted ablation studies to investigate the effectiveness of our proposed methods.