Title :
Bayesian regularization and nonnegative deconvolution for room impulse response estimation
Author :
Lin, Yuanqing ; Lee, Daniel D.
Author_Institution :
Dept. of Electr. & Syst. Eng., Univ. of Pennsylvania, Philadelphia, PA, USA
fDate :
3/1/2006 12:00:00 AM
Abstract :
This paper proposes Bayesian Regularization And Nonnegative Deconvolution (BRAND) for accurately and robustly estimating acoustic room impulse responses for applications such as time-delay estimation and echo cancellation. Similar to conventional deconvolution methods, BRAND estimates the coefficients of convolutive finite-impulse-response (FIR) filters using least-square optimization. However, BRAND exploits the nonnegative, sparse structure of acoustic room impulse responses with nonnegativity constraints and L1-norm sparsity regularization on the filter coefficients. The optimization problem is modeled within the context of a probabilistic Bayesian framework, and expectation-maximization (EM) is used to derive efficient update rules for estimating the optimal regularization parameters. BRAND is demonstrated on two representative examples, subsample time-delay estimation in reverberant environments and acoustic echo cancellation. The results presented in this paper show the advantages of BRAND in high temporal resolution and robustness to ambient noise compared with other conventional techniques.
Keywords :
Bayes methods; FIR filters; acoustic signal processing; architectural acoustics; deconvolution; echo suppression; least squares approximations; optimisation; probability; Bayesian regularization nonnegative deconvolution; FIR filters; acoustic room impulse response estimation; echo cancellation; expectation-maximization; finite-impulse-response; least-square optimization; probabilistic Bayesian framework; time-delay estimation; Acoustic applications; Acoustic noise; Bayesian methods; Context modeling; Deconvolution; Echo cancellers; Finite impulse response filter; Noise robustness; Optimization methods; Working environment noise; Bayesian regularization; echo cancellation; nonnegative deconvolution; time-delay estimation;
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2005.863030