Artificial Neural Networks and Support Vector Machine for Voice Disorders Identification
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2016, Vol 7, Issue 5
Abstract
The diagnosis of voice diseases through the invasive medical techniques is an efficient way but it is often uncomfortable for patients, therefore, the automatic speech recognition methods have attracted more and more interest recent years and have known a real success in the identification of voice impairments. In this context, this paper proposes a reliable algorithm for voice disorders identification based on two classification algorithms; the Artificial Neural Networks (ANN) and the Support Vector Machine (SVM). The feature extraction task is performed by the Mel Frequency Cepstral Coefficients (MFCC) and their first and second derivatives. In addition, the Linear Discriminant Analysis (LDA) is proposed as feature selection procedure in order to enhance the discriminative ability of the algorithm and minimize its complexity. The proposed voice disorders identification system is evaluated based on a widespread performance measures such as the accuracy, sensitivity, specificity, precision and Area Under Curve (AUC).
Authors and Affiliations
Nawel SOUISSI, Adnane CHERIF
Keywords
Related Articles
- EP ID EP133580
- DOI 10.14569/IJACSA.2016.070546
- Views 128
- Downloads 0
Bioinspired Immune System for Intrusions Detection System in Self Configurable Networks
In the last couple of years, the computer frameworks have become more vulnerable to external attacks. The PC security has become the prime cause of concern for every organization. To achieve this objective Intrusion Dete...
Smart Grids: A New Framework for Efficient Power Management in Datacenter Networks
The energy demand in the enterprise market segment demands a supply format that accommodates all generation and storage options with active participation by end users in demand response. Basically, with today’s hig...
Image Stitching System Based on ORB Feature-Based Technique and Compensation Blending
The construction of a high-resolution panoramic image from a sequence of input overlapping images of the same scene is called image stitching/mosaicing. It is considered as an important, challenging topic in computer vis...
A Penalized-Likelihood Image Reconstruction Algorithm for Positron Emission Tomography Exploiting Root Image Size
Iterative image reconstruction methods are considered better as compared to the analytical reconstruction methods in terms of their noise characteristics and quantification ability. Penalized-Likelihood Expectation Maxim...
Forensic Analysis using Text Clustering in the Age of Large Volume Data: A Review
Exploring digital devices in order to generate digital evidence related to an incident being investigated is essential in modern digital investigation. The emergence of text clustering methods plays an important role in...