An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds |
Foundation of Computer Science USA |
ICCTAC2015 - Number 1 |
May 2015 |
Authors: Salma Jabeen, K.m. Ravi Kumar |
52f2ee5d-75e7-4b05-aee4-ccb03ed8468a |
Salma Jabeen, K.m. Ravi Kumar . Effect of 0dB and 20dB Vehicle Noise on Stuttered Speech: A Study. An Architectural Framework for Workload Demand Prediction in Scalable Federated Clouds. ICCTAC2015, 1 (May 2015), 19-23.
This paper describes the effect of 0dB and 20dB vehicle noise on stuttered speech. 100 samples are collected from the subjects (stutterer), among which 80 samples are used for training and 20 samples for testing. The samples are trained using Mel Frequency Cepstral Coefficients (MFCC) feature extraction and statistical parameters such as mean, max, min, standard deviation (SD), power spectrum density (PSD), then the testing samples are analyzed by adding vehicle noise of 0dB and 20dB. Using sparse matrix enhancement technique the vehicle noise is degraded. The results obtained after enhancement are 45-95% depending on the samples used for analysis.