Speech denoising based on a greedy adaptive dictionary algorithm

In this paper we consider the problem of speech denoising based on a greedy adaptive dictionary (GAD) algorithm. The transform is orthogonal by construction, and is found to give a sparse representation of the data being analysed, and to be robust to additive Gaussian noise. The performance of the algorithm is compared to that of the principal component analysis (PCA) method, for a speech denoising application. It is found that the GAD algorithm offers a sparser solution than PCA, while having a similar performance in the presence of noise.

[1]  J. Nazuno Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[2]  Zhifeng Zhang,et al.  Adaptive Nonlinear Approximations , 1994 .

[3]  Mark D. Plumbley,et al.  An adaptive orthogonal sparsifying transform for speech signals , 2008, 2008 3rd International Symposium on Communications, Control and Signal Processing.

[4]  Rémi Gribonval,et al.  A survey of Sparse Component Analysis for blind source separation: principles, perspectives, and new challenges , 2006, ESANN.

[5]  Aapo Hyvärinen,et al.  Survey on Independent Component Analysis , 1999 .

[6]  Simon J. Godsill,et al.  Sparse Linear Regression With Structured Priors and Application to Denoising of Musical Audio , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[7]  Steven W. Zucker,et al.  Greedy Basis Pursuit , 2007, IEEE Transactions on Signal Processing.

[8]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[9]  Mark D. Plumbley,et al.  Separation of stereo speech signals based on a sparse dictionary algorithm , 2008, 2008 16th European Signal Processing Conference.

[10]  S. Haykin Unsupervised adaptive filtering, vol. 1: Blind source separation , 2000 .

[11]  Martin Vetterli,et al.  Atomic signal models based on recursive filter banks , 1997, Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136).

[12]  Martin Vetterli,et al.  Wavelets, approximation, and compression , 2001, IEEE Signal Process. Mag..

[13]  Arthur H. M. van Roermund,et al.  Unsupervised adaptive filtering, volume I: blind source separation [Book Review] , 2002, IEEE Circuits and Devices Magazine.

[14]  Stéphane Mallat,et al.  Audio Denoising by Time-Frequency Block Thresholding , 2008, IEEE Transactions on Signal Processing.