AUTOMATICALLY DERIVED SPOKEN LANGUAGE MARKERS FOR DETECTING MILD COGNITIVE IMPAIRMENT
| Citations: | 1 - 1 self |
BibTeX
@MISC{Roark_automaticallyderived,
author = {Brian Roark and John-paul Hosom and Margaret Mitchell and Jeffrey A. Kaye},
title = {AUTOMATICALLY DERIVED SPOKEN LANGUAGE MARKERS FOR DETECTING MILD COGNITIVE IMPAIRMENT},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Speech produced by subjects during neuropsychological exams can provide markers other than test performance, via spoken language characteristics that discriminate between subject groups. We present preliminary results on the utility of such markers, automatically derived from spoken responses to narrative recall tests, in discriminating between healthy elderly and subjects with Mild Cognitive Impairment (MCI). Given the audio and transcript of the retellings, a range of markers were automatically derived, including (among others) pause frequency and grammatical complexity. Certain spoken language derived markers, which do not measure the fidelity of the retelling to the original narrative, show statistically significant differences between the group means, when calculated either manually or automatically. 1.
