Computational and Mathematical Methods in Medicine / 2013 / Article / Tab 7

Research Article

Estimation of Phoneme-Specific HMM Topologies for the Automatic Recognition of Dysarthric Speech

Table 7

Recognition accuracies (WAcc) on the testing set with the baseline SD ASR and GA-op ASR systems (source data).

Level of dysarthriaSpeakerBaseline SD ASRGA-op ASR
Type% WAcc% WAcc

MildFBSD Bakis-1 (3, 6)81.2284.72
MHSD Bakis-1 (3, 6)80.3583.41
BBSD Bakis-1 (3, 6)77.5279.82
LLSD Bakis-1 (3, 6)74.1177.23

ModerateJFSD Bakis-1 (3, 6)64.0066.67
RLSD Bakis-1 (3, 6)51.1160.00
RKSD Ergodic (3, 6)39.9147.37

SevereBKSD Bakis-1 (3, 6)36.7346.46
BVSD Bakis-1 (3, 6)56.8261.82
SCSD Bakis-1 (3, 6)47.2754.55

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.