Computational and Mathematical Methods in Medicine / 2013 / Article / Tab 5

Research Article

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

Table 5

Recognition accuracies obtained with dysarthric-specific training schemes for the baseline SD ASR systems across all dysarthric speakers.

SpeakerSD Bakis-1SD Bakis-2SD ErgodicAverage

Mild scheme
FB81.2269.4376.8675.84
MH80.3572.4970.3174.38
BB77.5261.4763.7667.58
LL74.1166.9665.6368.90

Moderate scheme
JF64.0054.6752.0056.89
RL51.1147.1140.0046.07
RK39.4735.5339.9138.30

Severe scheme
BK36.7330.0930.5332.45
BV56.8253.6454.5555.00
SC47.2740.4541.8243.18

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.