# Analysing the Masked predictive coding training criterion for pre-training a Speech Representation Model

arXiv: https://arxiv.org/abs/2303.06982 · HTML: https://mlsanity.com/paper/2303.06982/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Mar 2023.

## Built on by (most cited first, 4 of 4)

- [What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis](https://mlsanity.com/paper/2401.17632/) (2024)
- [MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations](https://mlsanity.com/paper/2406.05661/) (2024)
- [JOOCI: a Framework for Learning Comprehensive Speech Representations](https://mlsanity.com/paper/2410.11086/) (2024)
- [Speech Representation Learning Revisited: The Necessity of Separate Learnable Parameters and Robust Data Augmentation](https://mlsanity.com/paper/2408.10557/) (2024)

## Abstract (arXiv)

Recent developments in pre-trained speech representation utilizing self-supervised learning (SSL) have yielded exceptional results on a variety of downstream tasks. One such technique, known as masked predictive coding (MPC), has been employed by some of the most high-performing models. In this study, we investigate the impact of MPC loss on the type of information learnt at various layers in the HuBERT model, using nine probing tasks. Our findings indicate that the amount of content information learned at various layers of the HuBERT model has a positive correlation to the MPC loss. Additionally, it is also observed that any speaker-related information learned at intermediate layers of the model, is an indirect consequence of the learning process, and therefore cannot be controlled using the MPC loss. These findings may serve as inspiration for further research in the speech community, specifically in the development of new pre-training tasks or the exploration of new pre-training criterion's that directly preserves both speaker and content information at various layers of a learnt model.