Analysis of Children’s Prosodic Features Using Emotion Based Utterances in Urdu Language
Journal Title: Engineering, Technology & Applied Science Research - Year 2018, Vol 8, Issue 3
Abstract
Emotion plays a significant role in identifying the states of a speaker using spoken utterances. Prosodic features add sense in spoken utterances providing speaker emotions. The objective of this research is to analyze the behavior of prosodic features (individual and in combination with others’ prosodic features) with different learning classifiers on emotion based utterances of children in the Urdu language. In this paper, three different prosodic features (intensity, pitch, formant and their combinations) with five different learning classifiers(ANN, J-48, K-star, Naïve Bayes, decision stump) and four basic emotions (happy, sad, angry, and neutral) were used to develop the experimental framework. Demonstrative experiments expressed that, in terms of classification accuracy, artificial neural networks show significant results with both individual and combination of prosodic features in comparison with other learning classifiers.
Authors and Affiliations
S. Khan, S. A. Ali, J. Sallar
Keywords
Related Articles
- EP ID EP168802
- DOI -
- Views 263
- Downloads 0
Cumulative Effect of Crumb Rubber and Steel Fiber on the Flexural Toughness of Concrete
Concrete properties, such as toughness and ductility, are enhanced to resist different impacts or blast loads. Rubberized concrete, which could be considered a green material, is produced from recycled waste tires grinde...
Effect of Time, Solvent-Solid Ratio, Ethanol Concentration and Temperature on Extraction Yield of Phenolic Compounds From Olive Leaves
This study aims to determine the factors affecting the process of extraction of phenolic compounds from olive leaves. Two methods of extraction were used in this work and different tests were implemented with the aim of...
Design and Simulation of a Decentralized Railway Traffic Control System
With the increasing use of railway transportation, various methods have been developed for the control and management of train traffic. Train traffic control systems that are currently in use are overwhelmingly centraliz...
Random Valued Impulse Noise Removal Using Region Based Detection Approach
Removal of random valued noisy pixel is extremely challenging when the noise density is above 50%. The existing filters are generally not capable of eliminating such noise when density is above 70%. In this paper a regio...
Impact of a Single Spoiler on Scouring Depth Status Beneath a River Crossing Inclined Pipeline
Deep river crossing pipelines utilized to carry fluids are often placed upon the sand bed. Placement of pipe on the non-smooth bed would result in the production of some local gaps beneath the pipe. Asymmetric scouring i...