InterSpeech 2013

Verbal communication through brain computer interfaces

Maureen Clerc, INRIA - Sophia Antipolis, France
Brain Computer Interfaces (BCI) provide a way of communicating directly from brain activity, bypassing muscular control. Research on BCI is concerned with designing reliable interaction protocols, and embedding them in systems that are both automatic and adaptive. Many types of brain activity are considered for BCI: some that are related to actual activity, such as imaginary motion or speech, and others that are not, such as evoked potentials or slow cortical potentials. This brain activity is measured through a diversity of modalities, either invasive or non-invasive. In this talk I report some recent advances in a BCI communication system called the P300 speller, which is a virtual brain-operated keyboard. This system relies on electroencephalographic activity time-locked to the flashing of the desired letters. It requires calibration of the system, but very little training from the user. Clinical tests are being conducted on a target population of patients suffering from Amyotrophic Lateral Sclerosis, in order to confirm the usability of the P300 speller for reliable communication.