Spectral Subtraction for Speech Enhancement and Compression Using LPC
Journal Title: International Journal of Computer Science & Engineering Technology - Year 2015, Vol 6, Issue 12
Abstract
Pre-Processing of Speech Signal is very crucial in the applications where silence or background noise is completely undesirable. The degradation of speech due to the presence of noise causes severe difficulties in various communication environments. Therefore, in this paper it is needed to first apply a noise removal and silence removal methods, in order to detect” clean” speech segments. Then using that clean speech the compression process was performed using the most powerful compression technique such as Linear Predictive Coding (LPC). Here different samples of spoken words are collected from different speakers and are used for implementation. The samples which is denoised, silence removed and compressed were compared with the samples which is not denoised but silence removed and compressed using LPC. Finally the results were evaluated in terms of compressed ratio (CR), Peak signal-to-noise ratio (PSNR) and Normalized root-mean square error (NRMSE).Finally the result show that the samples which is denoised, silence removed and compressed gives better result than the other samples.
Authors and Affiliations
Dr. D. Ambika , A. Deepa , P. Sumathi
A Cluster Based Optimization Technique with Adoptive Framework for ZigBee WSN
ZigBee is a current wireless standard based on IEEE 802.15.4 used in Wireless Sensor Networks (WSNs) stimulates many interests. In a built WSN, the information about some part of interest may need further research such t...
A MACHINE LEARNING APPROACH TO PREDICT SOLAR RADIATION FOR SOLAR ENERGY BASED DEVICES
Solar energy is used in many applications, such as increasing water’s temperature or moving electrons in a photovoltaic cell, agriculture planning, fuel production, electricity production, transport, architecture and urb...
Comparative Study of Different Clustering Algorithms for Association Rule Mining
In data mining, association rule mining is an important research area in today’s scenario. Various association rule mining can find interesting associations and correlation relationship among a large set of data items[1]...
An effective cluster formation with security in mobile ad hoc network
Mobile ad hoc networks have attracted much attention due to their mobility and easy deployment. However, the wireless and dynamic nature of network renders them more vulnerable to various types of security attacks than t...
Secret Detection of Sensitive Data Leakage
Surveys from many years have shown that many data leakages has been found due different problems like malicious attacks, hacking, different attacks. Approximately 28% of all data leakages are due to human mistakes which...