Show simple item record

dc.contributor.authorBrumberg, Jonathan S.en_US
dc.contributor.authorWright, E. Joeen_US
dc.contributor.authorAndreasen, Dinal S.en_US
dc.contributor.authorGuenther, Frank H.en_US
dc.contributor.authorKennedy, Philip R.en_US
dc.coverage.spatialSwitzerlanden_US
dc.date2011-04-24
dc.date.accessioned2018-02-08T14:28:55Z
dc.date.available2018-02-08T14:28:55Z
dc.date.issued2011
dc.identifierhttps://www.ncbi.nlm.nih.gov/pubmed/21629876
dc.identifier.citationJonathan S Brumberg, E Joe Wright, Dinal S Andreasen, Frank H Guenther, Philip R Kennedy. 2011. "Classification of intended phoneme production from chronic intracortical microelectrode recordings in speech-motor cortex.." Front Neurosci, Volume 5:65.
dc.identifier.issn1662-453X
dc.identifier.urihttps://hdl.handle.net/2144/26922
dc.description.abstractWe conducted a neurophysiological study of attempted speech production in a paralyzed human volunteer using chronic microelectrode recordings. The volunteer suffers from locked-in syndrome leaving him in a state of near-total paralysis, though he maintains good cognition and sensation. In this study, we investigated the feasibility of supervised classification techniques for prediction of intended phoneme production in the absence of any overt movements including speech. Such classification or decoding ability has the potential to greatly improve the quality-of-life of many people who are otherwise unable to speak by providing a direct communicative link to the general community. We examined the performance of three classifiers on a multi-class discrimination problem in which the items were 38 American English phonemes including monophthong and diphthong vowels and consonants. The three classifiers differed in performance, but averaged between 16 and 21% overall accuracy (chance-level is 1/38 or 2.6%). Further, the distribution of phonemes classified statistically above chance was non-uniform though 20 of 38 phonemes were classified with statistical significance for all three classifiers. These preliminary results suggest supervised classification techniques are capable of performing large scale multi-class discrimination for attempted speech production and may provide the basis for future communication prostheses.en_US
dc.description.sponsorshipR01 DC002852 - NIDCD NIH HHS; R44 DC007050 - NIDCD NIH HHSen_US
dc.format.extent65 - ?en_US
dc.languageeng
dc.relation.ispartofFront Neurosci
dc.rights© 2011 Brumberg, Wright, Andreasen, Guenther and Kennedy. This is an open-access article subject to a non-exclusive license between the authors and Frontiers Media SA, which permits use, distribution and reproduction in other forums, provided the original authors and source are credited and other Frontiers conditions are complied with.en_US
dc.subjectScience & technologyen_US
dc.subjectLife sciences & biomedicineen_US
dc.subjectNeurosciencesen_US
dc.subjectNeurosciences & neurologyen_US
dc.subjectLocked-in syndromeen_US
dc.subjectSpeech prosthesisen_US
dc.subjectNeurotrophic electrodeen_US
dc.subjectChronic recordingen_US
dc.subjectMotor cortexen_US
dc.subjectCognitive scienceen_US
dc.titleClassification of intended phoneme production from chronic intracortical microelectrode recordings in speech-motor cortexen_US
dc.typeArticleen_US
dc.identifier.doi10.3389/fnins.2011.00065
pubs.elements-sourcepubmeden_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Health & Rehabilitation Sciences: Sargent Collegeen_US
pubs.organisational-groupBoston University, College of Health & Rehabilitation Sciences: Sargent College, Speech, Language & Hearing Sciencesen_US
pubs.publication-statusPublished onlineen_US


This item appears in the following Collection(s)

Show simple item record