Content deleted Content added
opinionated, unsourced, ai text |
not sourced either! |
||
Line 157:
[[Edward Chang (neurosurgeon)|Edward Chang]] and Joseph Makin from [[UCSF Medical Center|UCSF]] reported that ECoG signals could be used to decode speech from epilepsy patients implanted with high-density ECoG arrays over the peri-Sylvian cortices.<ref>{{cite book | vauthors = Makin JG, Moses DA, Chang EF | title = Brain-Computer Interface Research | veditors = Guger C, Allison BZ, Gunduz A | chapter = Speech Decoding as Machine Translation|date=2021 |pages=23–33 |series=SpringerBriefs in Electrical and Computer Engineering|place=Cham|publisher=Springer International Publishing |language=en |doi=10.1007/978-3-030-79287-9_3 |isbn=978-3-030-79287-9 | s2cid = 239756345 }}</ref><ref>{{cite journal | vauthors = Makin JG, Moses DA, Chang EF | title = Machine translation of cortical activity to text with an encoder-decoder framework | journal = Nature Neuroscience | volume = 23 | issue = 4 | pages = 575–582 | date = April 2020 | pmid = 32231340 | doi = 10.1038/s41593-020-0608-8 | pmc = 10560395 | s2cid = 214704481 }}</ref> They reported word error rates of 3% (a marked improvement from prior efforts) utilizing an encoder-decoder [[neural network]], which translated ECoG data into one of fifty sentences composed of 250 unique words.
====Functional near-infrared spectroscopy====
|