A Hybrid Approach for Speech Signal Denoising using ICA-DWT

Lakshmikanth. S; Natraj. K. R; Rekha. K. R

In this paper problem considered is noise cancellation in speech signal corrupted by industrial noise. A Hybrid denoising method is presented as combination of Independent Component Analysis (ICA) and Discrete Wavelet Transform (DWT) for speech signal denoising. Independent component analysis is a computational method for separating a multivariate signal into additive subcomponents by assuming that the subcomponents are non-Gaussian signals and that they are all statistically independent of each other. Spatialfeatures in ICA is transformed into time and frequency domain with help of DWT. The experimental results shown that proposed hybrid algorithm has better performance on signal to noise ratio(SNR) and signal quality index(SQI) compared to FAST ICA algorithm

Select Volume / Issues:

• Volume 5,Issue 6, Nov. 2014

Year:

2014

Type of Publication:

Article

Keywords:

Speech Signal; Independent Component Analysis; Discrete Wavelet Transform; SNR; SQI

Journal:

IJECCE

Volume:

5

Number:

6

Pages:

1395-1399

Month:

November