# Resource-Efficient Fine-Tuning Strategies for Automatic MOS Prediction in Text-to-Speech for Low-Resource Languages

arXiv: https://arxiv.org/abs/2305.19396 · HTML: https://mlsanity.com/paper/2305.19396/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 30 May 2023.

## Builds on (most cited first, 16 of 16)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [The VoiceMOS Challenge 2022](https://mlsanity.com/paper/2203.11389/) (2022)
- [MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network](https://mlsanity.com/paper/2103.00110/) (2021)
- [LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech](https://mlsanity.com/paper/2110.09103/) (2021)
- [Utilizing Self-supervised Representations for MOS Prediction](https://mlsanity.com/paper/2104.03017/) (2021)
- [Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissions](https://mlsanity.com/paper/2009.03554/) (2020)
- [SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis](https://mlsanity.com/paper/2204.03040/) (2022)
- [Speech Quality Assessment through MOS using Non-Matching References](https://mlsanity.com/paper/2206.12285/) (2022)
- [Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis](https://mlsanity.com/paper/2002.12645/) (2020)

## Built on by (most cited first, 3 of 3)

- [Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection](https://mlsanity.com/paper/2306.12040/) (2023)
- [WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction](https://mlsanity.com/paper/2506.05899/) (2025)
- [The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speech](https://mlsanity.com/paper/2306.00535/) (2023)

## Abstract (arXiv)

We train a MOS prediction model based on wav2vec 2.0 using the open-access data sets BVCC and SOMOS. Our test with neural TTS data in the low-resource language (LRL) West Frisian shows that pre-training on BVCC before fine-tuning on SOMOS leads to the best accuracy for both fine-tuned and zero-shot prediction. Further fine-tuning experiments show that using more than 30 percent of the total data does not lead to significant improvements. In addition, fine-tuning with data from a single listener shows promising system-level accuracy, supporting the viability of one-participant pilot tests. These findings can all assist the resource-conscious development of TTS for LRLs by progressing towards better zero-shot MOS prediction and informing the design of listening tests, especially in early-stage evaluation.