Adaptive optimization based neural network for classification of stuttered speech

Abstract

Stuttering, also known as stammering is a speech disorder in which the fluency of speech is interrupted by occurrences of dysfluencies like repetitions, prolongations, and blocks or articulatory fixations. This work is intended to develop automatic recognition procedure to assess stuttering disfluencies (Repetitions, Prolongations and Blocks). For predicting the speech dysfluencies, we have employed an effective Adaptive Optimization based Artificial Neural Network (AOANN) approach. Moreover, the proposed technique employs the Mel Frequency Cepstral Coefficient (MFCC) features is implemented to test its effectiveness. The experimental investigations reveal that the proposed method shows promising results in distinguishing between three stuttering events repetitions, prolongations and blocks.