mlsanityData to 14 Oct 2026

Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction

arXiv 2312.15616 ↗First posted 25 Dec 2023cs.SD eess.AS stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Predicting audio quality in voice synthesis and conversion systems is a critical yet challenging task, especially when traditional methods like Mean Opinion Scores (MOS) are cumbersome to collect at scale. This paper addresses the gap in efficient audio quality prediction, especially in low-resource settings where extensive MOS data from large-scale listening tests may be unavailable. We demonstrate that uncertainty measures derived from out-of-the-box pretrained self-supervised learning (SSL) models, such as wav2vec, correlate with MOS scores. These findings are based on data from the 2022 and 2023 VoiceMOS challenges. We explore the extent of this correlation across different models and language contexts, revealing insights into how inherent uncertainties in SSL models can serve as effective proxies for audio quality assessment. In particular, we show that the contrastive wav2vec models are the most performant in all settings.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 14 of its 18 references that are in the map. First posted on arXiv 25 Dec 2023.

Builds on

14 of 18 references.

References · 14

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  5. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 298
  6. 2021TorchAudio: Building Blocks for Audio and Speech Processingcited by 83
  7. 2021Simple and Effective Zero-shot Cross-lingual Phoneme Recognitioncited by 79
  8. 2023TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorchcited by 27
  9. 2021Utilizing Self-supervised Representations for MOS Predictioncited by 20
  10. 2022SpeechLMScore: Evaluating speech generation using speech language modelcited by 20
  11. 2023The VoiceMOS Challenge 2023: Zero-shot Subjective Speech Quality Prediction for Multiple Domainscited by 8
  12. 2022DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scorescited by 7
2 more
  1. 2022Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained modelscited by 7
  2. 2023Dimensionality Reduction as Probabilistic Inferencecited by 4

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Modelscited by 4
  2. 2024Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collectioncited by 1
  3. 2025JSQA: Speech Quality Assessment with Perceptually-Inspired Contrastive Pretraining Based on JND Audio Pairscited by 1
  4. 2025Protein Language Model Zero-Shot Fitness Predictions are Improved by Inference-only Dropoutcited by 0