“…Among which, HMM is a parametric representation of time-varying features that simulate the human language processing and it needs a large number of samples for time-consuming training [7][8][9]. GMM is a probability density estimation model that can fit all probability distribution functions, but it depends heavily on data and it is sensitive to data noise [10][11][12]. SVM maps the feature vectors from input space to a high-dimensional Hilbert space by using kernel tricks at first and then seeks an optimal hyperplane in the high-dimensional space to classify samples.…”