Title :
Extension of the signal subspace speech enhancement approach to colored noise
Author :
Lev-Ari, Hanoch ; Ephraim, Yariv
Author_Institution :
Dept. of Electr. & Comput. Eng., Northeastern Univ., Boston, MA, USA
fDate :
4/1/2003 12:00:00 AM
Abstract :
The signal subspace approach for speech enhancement is extended to colored-noise processes. Explicit forms for the linear time-domain- and spectral-domain-constrained estimators are presented. These estimators minimize the average signal distortion power for given constraints on the residual noise power in the time and spectral domains, respectively. Equivalent implementations of the two estimators using the whitening approach are described.
Keywords :
random noise; spectral-domain analysis; speech enhancement; time-domain analysis; average signal distortion power; colored-noise processes; linear spectral-domain-constrained estimator; linear time-domain-constrained estimator; residual noise power; signal subspace approach; speech enhancement; whitening approach; Colored noise; Covariance matrix; Distortion; Equations; Karhunen-Loeve transforms; Signal design; Signal processing; Speech enhancement; Vectors; White noise;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2003.808544
