Automatic segmentation of phonemes during fast (/pa/ /ta/ /ka/) syllables repetition in hypokinetic dysarthria
Abstract
The aim of this study was to design an algorithm for automatic segmentation of consonants and vowels based upon a rapid steady /pa/-/ta/-/ka/ syllable repetition. Data for subsequent analysis were used from 24 patients with early stages of PD and 22 healthy subjects.
All syllables were manually labeled at three positions including explosion (E), vowel (V), and occlusion (O). In addition, the representative measurement of voice onset time (VOT) was included as difference between V and E position.
The three thresholds including 5 ms, 10 ms, and 20 ms were set up to test the accuracy of algorithm in finding proposed positions and VOT. When compared to the manual labeled positions, the VOT is detected within the range 5 ms to 20 ms with a range of a success rate of 68.2 – 90.5 %, 44.1 – 75.2 %, and 57.2 – 83.5% for normal, dysarthric, and all speakers.