Controlling robot using Thai Speech Recognition based on Eigen Sound

摘要

This paper presents a speech recognition technique, using commands of `Thai Speech Recognition' (TSR). The Fast Fourier Transform (FFT) and the Principal Component Analysis (PCA) are used to determine the spectrum and extract the feature of the speech signal of individual speaker, respectively. The Eigen Sound of individual speaker is generated via the extracted feature. The experimental results are demonstrated in a form of percentage of accuracy for different command words for both male and female.