Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/7027
Title: A wavelet based method for removal of highly non-stationary noises from single-channel hindi speech patterns of low input SNR
Authors: Singh S.
Tripathy, Manoj
Anand, Radhey Shyam
Published in: International Journal of Speech Technology
Abstract: This paper presents a binary mask thresholding function in Doubachies10 wavelet transform for enhancement of highly non-stationary noise mixed single-channel Hindi speech patterns of low (negative) SNR. In the wavelet transform, a five level of decomposition is used and detailed coefficients of all five levels are given to binary mask thresholding function for removing noise and enhancing the speech patterns. The robustness of the proposed method is compared with the wildly popular methods such as log-mmse, test-psc, Wiener, IdBM, and spectral-subtraction on the basis of performance measure parameters viz SNR, PSNR, PESQ, and Cepstrum distance. The algorithms were implemented in MATLAB 7.1. © 2014, Springer Science+Business Media New York.
Citation: International Journal of Speech Technology (2015), 18(2): 157-166
URI: https://doi.org/10.1007/s10772-014-9255-3
http://repository.iitr.ac.in/handle/123456789/7027
Issue Date: 2015
Publisher: Kluwer Academic Publishers
Keywords: Cepstrum distance
Hindi speech patterns
PESQ
SNR
Speech enhancement
Wavelet transform
ISSN: 13812416
Author Scopus IDs: 24757305000
16205441100
56363331000
Author Affiliations: Singh, S., Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Tripathy, M., Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Anand, R.S., Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, 247667, India
Corresponding Author: Singh, S.; Department of Electrical Engineering, Indian Institute of Technology RoorkeeIndia
Appears in Collections:Journal Publications [EE]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.