Overview of Automatic Stuttering Recognition System

Stuttering is a speech disorder. The flow of speech is disrupted by involuntary repetitions and prolongation of sounds, syllables, words or phrases, and involuntary silent pauses or blocks in communication. Stuttering is an interest subject of researchers from many various domains such as speech physiology & pathology, psychology, acoustic and signal analysis. Thus there are many researchers have been done previously. This paper presents an overview of previous works on automatic stuttering recognition system. Normally, classification of speech disorder is difficult and complicated. However some classification techniques associated with stuttering are commonly recognized. This paper review on classification techniques are utilized in automatic stuttering recognition for evaluating speech problem for stutterers. Some previous works discussed the different steps involved in recognizing stuttered speech from speech samples. This paper compares different classification techniques proposed by previous researchers. Classification techniques used in previous works are Artificial Neural Networks (ANNs), Hidden Markov Model (HMM) and Support Vector Machine (SVM).