What question did this study set out to answer?

This investigation aims to explore EEG signals to recognize unspoken speech and assess the impact of temporal effects on recognition performance.

January 1, 2009Open Access

EEG-BASED SPEECH RECOGNITION - Impact of Temporal Effects

View Full Paper

Ask AI

Bookmark

This investigation aims to explore EEG signals to recognize unspoken speech and assess the impact of temporal effects on recognition performance.
Conducted study with 21 subjects using 16 EEG channels in a 128 cap montage.
Tested recognition of unspoken words presented in blockwise, sequential, and random order.
Utilized HMM-based classifier, training with 5 words, each repeated 20 times.
Blockwise presentation achieved an average recognition rate of 45.50%.
Recognition dropped to chance level in sequential and random presentations.
Findings support the hypothesis that recorded EEG signals may reflect temporal correlated artifacts rather than actual words.

No takes yet. Share an insight, caveat, or question.

Randomized trial investigates EEG signals for unspoken speech recognition, suggesting artifacts influence outcomes.

Porbadnigk et al. (2009) studied this question.

View Full Paper

Ask AI

Bookmark