Imagined Speech Classification with EEG Signals for Silent Communication: A Preliminary Investigation into Synthetic Telepathy
Imagined Speech Classification with EEG Signals for Silent Communication: A Preliminary Investigation into Synthetic Telepathy
复制标题
用于无声交流的脑电图信号想象语音分类：综合心灵感应的初步研究
DOI：
10.1109/icbbe.2010.5515807
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
B. V. K. Vijaya Kumar
中科院分区：
文献类型：
--
作者：
Katharine Brigham;B. V. K. Vijaya Kumar
这项工作的目的是探索脑电(EEG)作为一种手段的潜在用途，通过从测量的脑电波中解码想象的语音来进行无声交流。加州大学欧文分校(UCI)记录了7名志愿者的脑电信号，他们想象着/ba/和/ku/两个音节，没有说话或执行任何公开的动作。我们的目标是对这些想象中的音节进行分类，并根据结果的准确性评估这项任务的可行性。本研究通过对脑电数据进行预处理以减少伪影和噪声的影响，并提取自回归(AR)系数作为特征，利用k近邻分类器进行想象音节分类。初步结果表明，识别想象的语音是可能的。
The objective of this work is to explore the potential use of electroencephalography (EEG) as a means for silent communication by way of decoding imagined speech from measured electrical brain waves. EEG signals were recorded at University of California, Irvine (UCI) from 7 volunteer subjects imagining two syllables, /ba/ and /ku/, without speaking or performing any overt actions. Our goal is to classify these imagined syllables and based on the resulting accuracy assess the feasibility of this task. In this research, the EEG data are preprocessed to reduce the effects of artifacts and noise, and autoregressive (AR) coefficients are extracted as features for imagined syllable classification using a k-Nearest Neighbor classifier. Initial results suggest that it is possible to identify imagined speech.