Abstract
Dysarthria is a neuromotor impairment of speech that affects one or more of the speech sub-systems. It is reflected in the acoustic characteristics of the phonemes as deviations from their healthy counterparts. To capture these deviations, in this work a continuous speech, an isolated-style monophone-based, and a triphone-based speech recognition systems are developed. These speech recognition systems are trained with the TIMIT speech corpus and tested with the Nemours database of dysarthric speech. The correlation coefficient between the performance of the speech recognition systems and the Frenchay dysarthria assessment (FDA) scores is computed for the assessment of articulatory sub-systems. It is observed that triphone-based system after necessary phoneme grouping based on place of articulation correlates well with the FDA scores. It is further observed that apart from the articulatory problems, some of the speakers are affected with velopharyngeal incompetence also. It is analyzed with group delay function-based acoustic measure for the detection of hypernasality on dysarthric speech and found that 4 out of 10 dysarthric speakers in the Nemours database are hypernasal.
