# The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domains

arXiv: https://arxiv.org/abs/2310.02640 · HTML: https://mlsanity.com/paper/2310.02640/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2023.

## Built on by (most cited first, 8 of 8)

- [The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech](https://mlsanity.com/paper/2409.09305/) (2024)
- [From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modeling](https://mlsanity.com/paper/2510.00743/) (2025)
- [Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction](https://mlsanity.com/paper/2312.15616/) (2023)
- [An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios](https://mlsanity.com/paper/2406.08911/) (2024)
- [Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings](https://mlsanity.com/paper/2509.03292/) (2025)
- [Zero-Shot vs. Few-Shot Multi-Speaker TTS Using Pre-trained Czech SpeechT5 Model](https://mlsanity.com/paper/2407.17167/) (2024)
- [Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions](https://mlsanity.com/paper/2509.24457/) (2025)
- [DAMOS: Learning Distortion-Aware Speech Quality Assessment through Explicit Distortion Localization](https://mlsanity.com/paper/2608.21176/) (2026)

## Abstract (arXiv)

We present the second edition of the VoiceMOS Challenge, a scientific event that aims to promote the study of automatic prediction of the mean opinion score (MOS) of synthesized and processed speech. This year, we emphasize real-world and challenging zero-shot out-of-domain MOS prediction with three tracks for three different voice evaluation scenarios. Ten teams from industry and academia in seven different countries participated. Surprisingly, we found that the two sub-tracks of French text-to-speech synthesis had large differences in their predictability, and that singing voice-converted samples were not as difficult to predict as we had expected. Use of diverse datasets and listener information during training appeared to be successful approaches.