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
Keywords
Related Articles
- EP ID EP148842
- DOI -
- Views 141
- Downloads 0
Centralized Bandwidth Distribution And Utility Provider
This paper is focused the problem faced by large offices and companies. It is helpful to keep observation on employees work for saving companies valuable time. Also it can control his activity. It provides server desktop...
Predictive time series analysis of stock prices using neural network classifier
The work pertains to developing financial forecasting systems which can be used for performing an in-depth analysis of the stocks prices, downloading/importing data from the various locations and analyzing that data and...
Flickr Distance: A Motion Prediction Approach for Visual Concepts
Image alignment has been studied in different areas of computer vision for hundreds of years, aligning images depicting different scenes remains a challenging problem. Variant to optical flow where an image is aligned to...
An Evaluation of A Country Based Anti- Phishing Approach Using Formal Methods
Phishing is a fraudulent attack that steals confidential information by mimicking a trustworthy entity in a medium of electronic communication. In this paper, research was conducted to evaluate a proposed country-based m...
HYBRID PERSONALIZED RECOMMENDATION APPROACH FOR IMPROVING MOBILE E-COMMERCE
In recent years, the massive influx of information onto internet has facilitated user, not only retrieving information, but also discovering facts. However, web users usually suffer from the information overload problem...