In a remarkable medical and scientific breakthrough, Frank Guenther of the Department of Cognitive and Neural Systems and Massachusetts Institute of Technology (MIT) among others have reached pivotal point in the field of thoughts to speech technology, where the scientists have successfully interpreted brain wave signals into speech and that too in real time. The conversion process took about 50 milliseconds on a paralyzed individual unable to express his thoughts in words.
The patient who participated in the study is a 26 years old individual who had suffered from a brain stem stroke at age at the early age of 16 and hadn’t been able to communicate vocally. The stroke left him paralyzed and created a lesion between the motor neurons and the brain, thus leaving him unable to carry out physical work.
The experiment began about five years ago, when the individual was implanted with an electrode at the borderline between premotor and primary motor cortex, that are specifically designed for speech function. The latest round of this experiment involved the feasibility tests of the implanted electrodes to see whether they are infact able to send neural signals to the machine that has been developed specifically to convert these signals into speech.
According to Frank Guenther,
“The study supported our hypothesis (based on the DIVA model, our neural network model of speech) that the premotor cortex represents intended speech as an ‘auditory trajectory,’ that is, as a set of key frequencies (formant frequencies) that vary with time in the acoustic signal we hear as speech. In other words, we could predict the intended sound directly from neural activity in the premotor cortex, rather than try to predict the positions of all the speech articulators individually and then try to reconstruct the intended sound (a much more difficult problem given the small number of neurons from which we recorded). This result provides our first insight into how neurons in the brain represent speech, something that has not been investigated before since there is no animal model for speech.”
Via Physorg.
