The outcomes proved the efficiency of the implemented feature selection algorithm. Classification techniques including Support Vector Machines (SVM), Random Forest and Artificial Neural Networks (ANN) are used for classifying the two categories. A speech dataset containing 141 different features, consisting of Mel-Frequency Cepstral Coefficients (MFCC), Linear Predictive Coefficients (LPC) among a few, is used. An optimization technique using the Fisher Discriminant Ratio is applied to identify distinct highlights from the discourse tests of the ID children and their age-matched control group. In this work, we investigate whether regular speech sentences could be utilized to distinguish between typically developed (TD) children with Intellectually Disabled (ID) children aged from 8 to 15 years. Classification of speech disorder is considered as a motivation to the research of speech processing, recognition and analysis. In human interaction, speakinghas a crucial partwhen it comes to expressing ideas and thoughts.
0 kommentar(er)
