Thai speech assessment based on fractal theory

This paper proposes the novel method to assess Thai speech based on fractal analysis. The fractal algorithm, namely, Higuchi's method was selected to evaluate the fractal dimension (FD) of segmented speech signals. To show the FD changes in waveform over time, the time-dependent FD (TDFD) was proposed. Probability distribution of TDFDs using kernel density estimation was used as an additional parameter. The proposed method achieves the average percentages of assessment with successful rates of 90.0% (+8.9%) and 88.1% (+12.5%) for single and double syllables of Thai speech, respectively.