# Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis

arXiv: https://arxiv.org/abs/2507.06116 · HTML: https://mlsanity.com/paper/2507.06116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts.
- Builds on 5 of its 6 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Placed in

- Mixture-of-experts / [Multimodal MoE models](https://mlsanity.com/moe/multimodal-moe-models/)

## Builds on (most cited first, 5 of 5)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications](https://mlsanity.com/paper/2409.03283/) (2024)

## Abstract (arXiv)

Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper proposes an enhanced MOS prediction system based on self-supervised learning speech models, incorporating a Mixture of Experts (MoE) classification head and utilizing synthetic data from multiple commercial generation models for data augmentation. Our method builds upon existing self-supervised models such as wav2vec2, designing a specialized MoE architecture to address different types of speech quality assessment tasks. We also collected a large-scale synthetic speech dataset encompassing the latest text-to-speech, speech conversion, and speech enhancement systems. However, despite the adoption of the MoE architecture and expanded dataset, the model's performance improvements in sentence-level prediction tasks remain limited. Our work reveals the limitations of current methods in handling sentence-level quality assessment, provides new technical pathways for the field of automatic speech quality assessment, and also delves into the fundamental causes of performance differences across different assessment granularities.