An Approach for Classification of Dysfluent and Fluent Speech Using K-NN And SVM

TL;DR

This study develops a classification method for distinguishing dysfluent from fluent speech using MFCC features and machine learning classifiers, achieving over 86% accuracy in identifying speech fluency status.

Contribution

It introduces a novel application of MFCC features combined with k-NN and SVM classifiers for speech fluency classification, focusing on specific dysfluency types.

Findings

Achieved 86.67% accuracy for dysfluent speech

Achieved 93.34% accuracy for fluent speech

Demonstrated effectiveness of MFCC with machine learning classifiers

Abstract

This paper presents a new approach for classification of dysfluent and fluent speech using Mel-Frequency Cepstral Coefficient (MFCC). The speech is fluent when person's speech flows easily and smoothly. Sounds combine into syllable, syllables mix together into words and words link into sentences with little effort. When someone's speech is dysfluent, it is irregular and does not flow effortlessly. Therefore, a dysfluency is a break in the smooth, meaningful flow of speech. Stuttering is one such disorder in which the fluent flow of speech is disrupted by occurrences of dysfluencies such as repetitions, prolongations, interjections and so on. In this work we have considered three types of dysfluencies such as repetition, prolongation and interjection to characterize dysfluent speech. After obtaining dysfluent and fluent speech, the speech signals are analyzed in order to extract MFCC features. The k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) classifiers are used to classify the speech as dysfluent and fluent speech. The 80% of the data is used for training and 20% for testing. The average accuracy of 86.67% and 93.34% is obtained for dysfluent and fluent speech respectively.