Speech Enhancement Using Wavelet Neural Network with Sub-Band Adaptive Matched Filter

Dan Yang; Bin Xu; Lin Lin Ye; Xu Wang

doi:10.4028/www.scientific.net/AEF.2-3.127

Paper Titles

Removal of Ocular Artifact from EEG Using Constrained ICA
p.105

HHT Based Analysis on Experiments of Rotor System with Rub-Impact
p.111

Energy Analysis Method Based on Wavelet Transform for Sensor Fault Diagnosis
p.117

Research on the Peripheral Sound Visualization Using the Improved Ripple Mode
p.123

Speech Enhancement Using Wavelet Neural Network with Sub-Band Adaptive Matched Filter
p.127

Design and Implementation of Sensor Network Device Control System with AR Technology
p.131

Speech Endpoint Detection in Noisy Environment Based on the Ensemble Empirical Mode Decomposition
p.135

Simulation Analysis on Cymbal Transducer
p.140

Research on the Broadband Dual-Excited Underwater Acoustic Transducer
p.144

HomeAdvanced Engineering ForumAdvanced Engineering Forum Vols. 2-3Speech Enhancement Using Wavelet Neural Network...

Speech Enhancement Using Wavelet Neural Network with Sub-Band Adaptive Matched Filter

Abstract:

Wavelet Neural Network (WNN) Is a Time-frequency Analysis Method, which Detects the Subtle Small Changes in the Signal Frequency Domain. Adaptive Filter Provides a Kind of Simple and Applied Method for Processing Signals in Noise. in this Paper, we Proposed a New Speech Enhancement Technique which Is Based on Wavelet Neural Network Using Adaptive Matched Filter Adjusting Weight. we Choose the Signal with Noise Pollution as the Input Signal and then Put it to the Trained Wavelet Neural Network. Wavelet Decomposition and Wavelet Neural Network Weights Processing Adopt Signal Sub-band Adaptive Matched Filter, the Output Signal of Wavelet Neural Network Is an Approximation Form of Original Signal. the Results Show that the WNN Is a Quite Effective Method for the Speech Enhancement and Improving the Ration of Signal to Noise.

By email View Pdf

You have full access to the following eBook

Read eBook

Info:

Periodical:

Advanced Engineering Forum (Volumes 2-3)

Pages:

127-130

DOI:

https://doi.org/10.4028/www.scientific.net/AEF.2-3.127

Citation:

Cite this paper

Online since:

December 2011

Authors:

Dan Yang, Bin Xu, Lin Lin Ye, Xu Wang

Keywords:

Speech Enhancement, Sub-Band Adaptive Matched, Time-Frequency Analysis, Wavelet Neural Network (WNN)

Export:

RIS, BibTeX

Permissions:

Creative Commons CC BY 4.0

Citation:

References

[1] Hac1Tasmaza, Ergun, Ercelebi., speech enhancement based on undecimated wavelet-perceptual filterbanks and MMSE-STSA estimation invarious noise environments[J], Digital Signal Processing, 2008. 18: 797–812.

DOI: 10.1016/j.dsp.2007.10.003

Google Scholar

[2] Mohammed Bahoura, Jean Rouat, Wavelet speech enhancement based on time–scale adaptation[J], Speech Communication, 2006. 48(12): 1620-1637.

DOI: 10.1016/j.specom.2006.06.004

Google Scholar

[3] Xu J, Ho DWC. A basis selection algorithm for wavelet neural Networks[J]. Neurocomputing 2002; 48: 681–689.

DOI: 10.1016/s0925-2312(01)00638-5

Google Scholar

[4] Subasi A, Alkan A, Koklukaya E, Kiymik MK. Wavelet neural network classification of EEG signals by using AR model with MLE preprocessing[J], Neural Networks 2005; 18(7): 985–97.

DOI: 10.1016/j.neunet.2005.01.006

Google Scholar

[5] Xuegin Zhao, Jinaming Lu, Putranto, W.P.A., Yahagi, T. Nonlinear time series prediction using wavelet networks with Kalman filter based algorithm[C], IEEE conference on Industrial technology, 2005, 1226-1230.

DOI: 10.1109/icit.2005.1600822

Google Scholar

[6] Wei Zhang, Xu Wang, Linlin Ge et al. Simulation of weak signal detection based on wavelet analysis[C], The Proceedings of the 11th International Conference on Industrial Engineering and Engineering Management(IEE), 2005-04: 652-656.

Google Scholar

[7] Qinghua Zhang, Alber Benvensite. Wavelet Networks[J], IEEE transactions on neural networks, 1992. 3(6): 889-899.

Google Scholar