|International Journal of Applied Information Systems|
|Foundation of Computer Science (FCS), NY, USA|
|Volume 10 - Number 4|
|Year of Publication: 2016|
|Authors: Monica Mundada, Sangramsing N. Kayte|
Monica Mundada, Sangramsing N. Kayte . Analysis of Speech and its Fluency Disorders. International Journal of Applied Information Systems. 10, 4 ( January 2016), 10-12. DOI=10.5120/ijais2016451484
The oldest way of communication and information exchange between human beings is speech. It is the most prominent and natural form of communication between humans. Speech has potential of being important mode of interaction with computer. The communication among human and computer is called human computer interaction. Man machine interface have always proved a challenging area in natural language processing and in speech recognition research. The primary aim of the study is to distinguish the difference between normal and abnormal speech. It aims to prepare a layout of factors for different types of speech and voices and its core production system. The speech disorders like misarticulation and stammering are studied with its features and associated existing therapies. The distinction is experimented with various techniques such as MFCC, DTW and K-means. The mean value of MFCC coefficients are explored for speech disorders and normal speech samples. The Euclidean distance measure is calculated between normal and abnormal speech and the variations lying in them are studied further. t-test is also experimented to justify the classification result.