Open-vocabulary Auditory Neural Decoding Using fMRI-prompted LLM

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xiaoyu, Du, Changde, Liu, Che, Wang, Yizhe, He, Huiguang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913348465983488
author Chen, Xiaoyu
Du, Changde
Liu, Che
Wang, Yizhe
He, Huiguang
author_facet Chen, Xiaoyu
Du, Changde
Liu, Che
Wang, Yizhe
He, Huiguang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_07840
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-vocabulary Auditory Neural Decoding Using fMRI-prompted LLM
Chen, Xiaoyu
Du, Changde
Liu, Che
Wang, Yizhe
He, Huiguang
Human-Computer Interaction
Computation and Language
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.
title Open-vocabulary Auditory Neural Decoding Using fMRI-prompted LLM
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2405.07840