Open-vocabulary Auditory Neural Decoding Using fMRI-prompted LLM

TL;DR

This paper presents BP-GPT, a novel brain decoding method that uses fMRI-derived brain prompts with GPT-2 to decode open-vocabulary auditory semantic information, outperforming previous methods.

Contribution

The paper introduces BP-GPT, a new approach leveraging brain prompts with GPT-2 for open-vocabulary neural decoding from fMRI signals, enhancing decoding robustness and accuracy.

Findings

Achieved up to 4.61% improvement on METEOR score.

Achieved up to 2.43% improvement on BERTScore.

Demonstrated feasibility of using brain prompts with LLMs for neural decoding.

Abstract

Decoding language information from brain signals represents a vital research area within brain-computer interfaces, particularly in the context of deciphering the semantic information from the fMRI signal. However, many existing efforts concentrate on decoding small vocabulary sets, leaving space for the exploration of open vocabulary continuous text decoding. In this paper, we introduce a novel method, the \textbf{Brain Prompt GPT (BP-GPT)}. By using the brain representation that is extracted from the fMRI as a prompt, our method can utilize GPT-2 to decode fMRI signals into stimulus text. Further, we introduce a text-to-text baseline and align the fMRI prompt to the text prompt. By introducing the text-to-text baseline, our BP-GPT can extract a more robust brain prompt and promote the decoding of pre-trained LLM. We evaluate our BP-GPT on the open-source auditory semantic decoding dataset and achieve a significant improvement up to $4.61\%$ on METEOR and $2.43\%$ on BERTScore across all the subjects compared to the state-of-the-art method. The experimental results demonstrate that using brain representation as a prompt to further drive LLM for auditory neural decoding is feasible and effective.