mlsanityData to 7 Oct 2026

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

arXiv 2305.19396 ↗First posted 30 May 2023eess.AS cs.CLcited by 3

Not on the map. Why?

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 30 May 2023.

Builds on

16 of 28 references.

References · 16

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  5. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  6. 2021A Survey on Neural Speech Synthesiscited by 182
  7. 2019MOSNet: Deep Learning based Objective Assessment for Voice Conversioncited by 126
  8. 2021Generalization Ability of MOS Prediction Networkscited by 69
  9. 2022The VoiceMOS Challenge 2022cited by 57
  10. 2021MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Networkcited by 37
  11. 2021LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speechcited by 24
  12. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
4 more
  1. 2020Predictions of Subjective Ratings and Spoofing Assessments of Voice Conversion Challenge 2020 Submissionscited by 19
  2. 2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesiscited by 18
  3. 2022Speech Quality Assessment through MOS using Non-Matching Referencescited by 16
  4. 2020Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesiscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Strategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selectioncited by 2
  2. 2025WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Predictioncited by 2
  3. 2023The Effects of Input Type and Pronunciation Dictionary Usage in Transfer Learning for Low-Resource Text-to-Speechcited by 0