Academic Journals Database
Disseminating quality controlled scientific knowledge

DUAL CHANNEL SPEECH ENHANCEMENT USING HADAMARD-LMS ALGORITHM WITH DCT PREPROCESSING TECHNIQUE

ADD TO MY LIST
 
Author(s): D.DEEPA, | Dr. A. SHANMUGAM

Journal: International Journal of Engineering Science and Technology
ISSN 0975-5462

Volume: 2;
Issue: 9;
Start page: 4418;
Date: 2010;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Sensorineural loss | SNR | MSE | Hadamard transform | DCT | LMS.

ABSTRACT
Speech enhancement and noise reduction have wide applications in speech processing. They are often employed as a pre-processing stage in various applications. Two points are often required to be considered in signal de-noising applications: eliminating the undesired noise from signal to improve the Signal to noise Ratio(SNR) and preserving the shape and characteristics of the original signal. Background noise in speech signal will reduce the speech intelligibility for people with hearing loss especially for sensorineural loss patients. The proposed algorithm describes Hadamard - Least Mean Square algorithm with DCT pre processing technique to improve the SNR and to reduce the mean square error (MSE). The DCT has separable, and energy compaction property. Although the DCT does not separate frequencies, it is a powerful signal decorrelator. It is a real valued function and thus can be effectively used in real-time operation.
Affiliate Program      Why do you need a reservation system?