# Refining Self-Supervised Learnt Speech Representation using Brain Activations

arXiv: https://arxiv.org/abs/2406.08266 · HTML: https://mlsanity.com/paper/2406.08266/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2024.

## Built on by (most cited first, 1 of 1)

- [Better audio representations are more brain-like: linking model-brain alignment with performance in downstream auditory tasks](https://mlsanity.com/paper/2511.16849/) (2025)

## Abstract (arXiv)

It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream tasks can further improve the similarity. However, it still remains unclear if this similarity can be used to optimize the pre-trained speech models. In this work, we therefore propose to use the brain activations recorded by fMRI to refine the often-used wav2vec2.0 model by aligning model representations toward human neural responses. Experimental results on SUPERB reveal that this operation is beneficial for several downstream tasks, e.g., speaker verification, automatic speech recognition, intent classification.One can then consider the proposed method as a new alternative to improve self-supervised speech models.