Detecting type and severity of speech impairment using deep-learning and machine learning algorithms

Chatterjee, Ankit (2023) Detecting type and severity of speech impairment using deep-learning and machine learning algorithms. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (775kB) | Preview

Abstract

Speech forms an important aspect of human life as it is one of the main forms of communication. Speech impairment refers to a condition that affects a person’s verbal communication. There are several types of speech impediments like stuttering/stammering, aphasia, dysarthria, mutism, etc. Previous studies have used distinct deep-learning methods like neural networks to explore the area of speech recognition and emotion classification using audio data. However, the aspect of classification of the different types of speech disorders still needs to be analyzed in depth. This paper not only attempts to classify speech disorders through audio files but also attempts to detect the severity of those disorders.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham UNSPECIFIED
Uncontrolled Keywords:	Long Short-Term Method; Recursive Neural Network; Empirical Mode Decomposition; Wavelet Transform; MFCC; Savitzky Golay Smoothing Technique
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RB Pathology Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	08 Nov 2024 12:41
Last Modified:	08 Nov 2024 12:41
URI:	https://norma.ncirl.ie/id/eprint/7173

Actions (login required)

View Item