MedPage Today (8/23, George) reports, “High-performance brain-computer interfaces…decoded brain activity into speech faster, more accurately, and with a bigger vocabulary than existing technologies, two early trials…showed.” Researchers found “in the BrainGate2 study, speech-to-text BCI that recorded activity from intracortical microelectrode arrays…decoded the speech of a woman with amyotrophic lateral sclerosis…at 62 words per minute, more than 3 times faster than the previous record.” Meanwhile, “in the BRAVO study,” investigators “reported success in three modalities – text, speech audio, and facial-avatar animation – using high-density surface recordings of the speech cortex.” MedPage Today adds, “Decoding the text of a woman with a brainstem stroke reached a median rate of 78 words per minute, and the participant was able to ‘speak’ through a digital avatar with software that simulated facial movements.” The findings were published in Nature.
Related Links:
— MedPage Today (requires login and subscription)