Brain wave recognition of words

Abstract

Electrical and magnetic brain waves of seven subjects under three experimental conditions were recorded for the purpose of recognizing which one of seven words was processed. The analysis consisted of averaging over trials to create prototypes and test samples, to both of which Fourier transforms were applied, followed by filtering and an inverse transformation to the time domain. The filters used were optimal predictive filters, selected for each subject and condition. Recognition rates, based on a least-squares criterion, varied widely, but all but one of 24 were significantly different from chance. The two best were above 90%. These results show that brain waves carry substantial information about the word being processed under experimental conditions of conscious awareness.In the last two decades new methods of imaging brain activity [positron emission tomography, functional magnetic resonance imaging, and magnetoencephalography (MEG)] have augmented older methods such as electroencephalography (EEG) to dramatically increase our knowledge, especially about where in the brain different kinds of activity occur (1-5). Increased knowledge of temporal sequence of location of activity, as in orally naming a visual object, also has been substantial (6). On the other hand, aside from some success in simple mental state classification (7,8) and EEG-based human computer communications (9, 10), the detailed analyses of how or what information is processed by the brain, at almost all levels, are still mostly lacking (11). Early attempts to classify averaged EEG waveforms associated with speech production date back to 1967 (12). However, it was later discovered (13) that scalp-recorded potentials preceding and accompanying speech primarily represent volume-conducted activity from musculature involved in speech production. In the current study, we were careful to rule out contributions from muscle movement in the auditory comprehension and internal speech conditions.The research reported here is meant to be a definitely positive, even if limited, step toward giving such an analysis of brain-wave activity as imaged by EEG and MEG. The brief description of our approach is simple. We analyze brain waves to recognize the word being processed. The general methodological approach is similar to speech recognition, but almost all the details are different. In terms of performance, we are at a level comparable to that of speech recognition in its early days (14, 15). METHODSFor subjects S1-S5, EEG and MEG recordings were performed simultaneously in a magnetically shielded room in the Magnetic Source Imaging Laboratory (Biomagnetic Technology, San Diego) housed in Scripps Institute of Research.Sixteen EEG sensors were used. Specifically, the sensors, referenced to the average of the left and the right mastoids, were attached to the scalp of a subject (F7, T3, T5, FP1, F3, C3, P3, Fz, Cz, FP2, F4, C4, P4, F8, T4, and T6); sensors FP1, Fz, and FP2 were not used with S1 and S2. Two electrooculogram sensors, referenced to each ...

Brain-wave representation of words by superposition of a few sine waves

“…By using all of the data again to create eight unfiltered but averaged test samples and by applying a least-squares criterion of fit, we correctly classified six of the eight syllables. This is a reasonably good result but not as good as the use of an optimal filter, as in earlier articles (1)(2)(3)(4). By using data from sensor C3 and the time interval from 107 ms after onset of stimuli to 640 ms, the optimal filtered result was classification of all eight unfiltered test samples correctly.…”

“…Subjects were numbered consecutively and sometimes were used in more than one of the earlier studies (1)(2)(3)(4). The same numbering is used in this article.…”

Name that tune: Decoding music from the listening brain

“…One example is a study by Bhattacharya et al (2001), who found different patterns of dependencies between EEG channels while listening to different pieces of music, which are higher for listeners with musical training than for nonmusicians. Early studies on classifying auditorily presented language (words or sentences) produced good results (Suppes et al, 1997(Suppes et al, , 1998, indicating feasibility of classification using EEG signals, but to our knowledge no such effort has been made for musical material.…”

EEG-BASED SPEECH RECOGNITION - Impact of Temporal Effects

“…In (Suppes et al, 1997), it has been shown that isolated words can be recognized based on EEG and MEG recordings. In one of their experimental conditions called internal speech, the subjects were shown one out of 12 words on a screen and asked to utter this word 'silently' without using any articulatory muscles.…”

“…However, it has been shown in (Suppes et al, 1997) that subject-independent predictions are possible. It has to be taken into account, though, that their subject-independent model was built by averaging over half of their database which was much larger than ours.…”