Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Syncope as the Initial Presentation of Takayasu Arteritis in a 57-Year-Old Female: A Case Report and Literature Review.

Clinical case reports·2026

Same author

Electrical muscle stimulation towards self-physiotherapy on myofascial pain syndrome.

Frontiers in rehabilitation sciences·2026

Same author

TaWRKY33 Positively Regulates TaERF1-A, Thereby Activating TaP5CS<sub>2</sub> <sup>-</sup>Mediated Proline Biosynthesis, Which Enhances Drought Tolerance in Wheat (Triticum aestivum L.).

Plant, cell & environment·2026

Same author

Left Main Coronary Dissection Masquerading in Pediatric Polytrauma: A Diagnostic Challenge.

JACC. Case reports·2026

Same author

Towards objective identification of myofascial trigger points: A high-density surface electromyography method.

Computers in biology and medicine·2026

Same author

Stage-dependent modulation of high- and low-frequency neural activity during motor imagery based on stereoelectroencephalography.

NeuroImage·2026

Search research articles

相关实验视频

Updated: Jun 23, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

使用先进的深度学习方法,从立体电脑学 (sEEG) 信号中解读语音.

Xiaolong Wu¹, Scott Wellington¹, Zhichun Fu¹

¹Department of Electronic and Electrical Engineering, University of Bath, Bath, United Kingdom.

Journal of neural engineering

|June 17, 2024

概括

此摘要是机器生成的。

这项研究表明,先进的深度学习模型可以从立体脑电图 (sEEG) 信号中解码口语荷兰语. 这些发现凸显了sEEG在恢复语言障碍患者的沟通潜力.

关键词:

大脑计算机接口 (BCI)深度学习是一种深度学习.语音解码语音解码语音解码语言假肢语音假肢立体电脑电图 (sEEG) 是一种立体电脑电图.

更多相关视频

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

相关实验视频

Last Updated: Jun 23, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology

Published on: June 29, 2021

科学领域:

神经科学是一个神经科学.
生物医学工程生物医学工程
人工智能的人工智能

背景情况:

大脑-计算机接口 (BCI) 提供了一种通过解码大脑信号来恢复通信的方式.
虽然诸如微电极阵列和电皮录像等侵入性方法在语音BCI中很常见,但立体电脑录像 (sEEG) 的研究较少.
恢复语言障碍患者的沟通是神经科学和医学中的一个重大挑战.

研究的目的:

研究立体电脑学 (sEEG) 对于解码口语的有效性.
将深度学习模型的性能与使用sEEG数据的传统语音解码方法进行比较.
探索基于sEEG的BCI在语音恢复方面的潜力.

主要方法:

利用最近发布的sEEG数据从讲荷兰语的患者参与者.
实现并比较了三个解码方法:线性回归,基于循环神经网络 (RNN) 的序列对序列模型和变压器模型.
应用了先进的深度学习技术,直接从sEEG信号中解码语音波形.

主要成果:

在语音解码中,RNN和变压器模型都显著超过了线性回归方法.
在RNN和变压器模型之间没有观察到显著的性能差异.
语音解码只能使用sEEG电极的子集来实现,这表明电极位置的重要性.

结论:

从sEEG信号解读语音是可行的,并使用深度学习有效.
sEEG电极的精确位置是影响语音解码性能的一个关键因素.
sEEG为开发高级语音恢复大脑计算机接口提供了一种可行的,但尚未充分利用的模式.