Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Hui, Wang, Hai-Teng, Jiang, Wei-Bang, Chen, Zhong-Tao, He, Li, Lin, Pei-Yang, Wei, Peng-Hu, Zhao, Guo-Guang, Liu, Yun-Zhe
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.11459
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915001335283712
author Zheng, Hui
Wang, Hai-Teng
Jiang, Wei-Bang
Chen, Zhong-Tao
He, Li
Lin, Pei-Yang
Wei, Peng-Hu
Zhao, Guo-Guang
Liu, Yun-Zhe
author_facet Zheng, Hui
Wang, Hai-Teng
Jiang, Wei-Bang
Chen, Zhong-Tao
He, Li
Lin, Pei-Yang
Wei, Peng-Hu
Zhao, Guo-Guang
Liu, Yun-Zhe
contents Invasive brain-computer interfaces with Electrocorticography (ECoG) have shown promise for high-performance speech decoding in medical applications, but less damaging methods like intracranial stereo-electroencephalography (sEEG) remain underexplored. With rapid advances in representation learning, leveraging abundant recordings to enhance speech decoding is increasingly attractive. However, popular methods often pre-train temporal models based on brain-level tokens, overlooking that brain activities in different regions are highly desynchronized during tasks. Alternatively, they pre-train spatial-temporal models based on channel-level tokens but fail to evaluate them on challenging tasks like speech decoding, which requires intricate processing in specific language-related areas. To address this issue, we collected a well-annotated Chinese word-reading sEEG dataset targeting language-related brain networks from 12 subjects. Using this benchmark, we developed the Du-IN model, which extracts contextual embeddings based on region-level tokens through discrete codex-guided mask modeling. Our model achieves state-of-the-art performance on the 61-word classification task, surpassing all baselines. Model comparisons and ablation studies reveal that our design choices, including (i) temporal modeling based on region-level tokens by utilizing 1D depthwise convolution to fuse channels in the ventral sensorimotor cortex (vSMC) and superior temporal gyrus (STG) and (ii) self-supervision through discrete codex-guided mask modeling, significantly contribute to this performance. Overall, our approach -- inspired by neuroscience findings and capitalizing on region-level representations from specific brain regions -- is suitable for invasive brain modeling and represents a promising neuro-inspired AI approach in brain-computer interfaces.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11459
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
Zheng, Hui
Wang, Hai-Teng
Jiang, Wei-Bang
Chen, Zhong-Tao
He, Li
Lin, Pei-Yang
Wei, Peng-Hu
Zhao, Guo-Guang
Liu, Yun-Zhe
Signal Processing
Computation and Language
Neurons and Cognition
Invasive brain-computer interfaces with Electrocorticography (ECoG) have shown promise for high-performance speech decoding in medical applications, but less damaging methods like intracranial stereo-electroencephalography (sEEG) remain underexplored. With rapid advances in representation learning, leveraging abundant recordings to enhance speech decoding is increasingly attractive. However, popular methods often pre-train temporal models based on brain-level tokens, overlooking that brain activities in different regions are highly desynchronized during tasks. Alternatively, they pre-train spatial-temporal models based on channel-level tokens but fail to evaluate them on challenging tasks like speech decoding, which requires intricate processing in specific language-related areas. To address this issue, we collected a well-annotated Chinese word-reading sEEG dataset targeting language-related brain networks from 12 subjects. Using this benchmark, we developed the Du-IN model, which extracts contextual embeddings based on region-level tokens through discrete codex-guided mask modeling. Our model achieves state-of-the-art performance on the 61-word classification task, surpassing all baselines. Model comparisons and ablation studies reveal that our design choices, including (i) temporal modeling based on region-level tokens by utilizing 1D depthwise convolution to fuse channels in the ventral sensorimotor cortex (vSMC) and superior temporal gyrus (STG) and (ii) self-supervision through discrete codex-guided mask modeling, significantly contribute to this performance. Overall, our approach -- inspired by neuroscience findings and capitalizing on region-level representations from specific brain regions -- is suitable for invasive brain modeling and represents a promising neuro-inspired AI approach in brain-computer interfaces.
title Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
topic Signal Processing
Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2405.11459