Title :
A generalized subspace approach for enhancing speech corrupted by colored noise
Author :
Hu, Yi ; Loizou, Philipos C.
Author_Institution :
Dept. of Electr. Eng., Univ. of Texas, Richardson, TX, USA
fDate :
7/1/2003 12:00:00 AM
Abstract :
A generalized subspace approach is proposed for enhancement of speech corrupted by colored noise. A nonunitary transform, based on the simultaneous diagonalization of the clean speech and noise covariance matrices, is used to project the noisy signal onto a signal-plus-noise subspace and a noise subspace. The clean signal is estimated by ing the signal components in the noise subspace and retaining the components in the signal subspace. The applied transform has built-in prewhitening and can therefore be used in general for colored noise. The proposed approach is shown to be a generalization of the approach proposed by Y. Ephraim and H.L. Van Trees (see ibid., vol.3, p.251-66, 1995) for white noise. Two estimators are derived based on the nonunitary transform, one based on time-domain constraints and one based on spectral domain constraints. Objective and subjective measures demonstrate improvements over other subspace-based methods when tested with TIMIT sentences corrupted with speech-shaped noise and multi-talker babble.
Keywords :
Karhunen-Loeve transforms; acoustic noise; covariance matrices; parameter estimation; random noise; spectral-domain analysis; speech enhancement; time-domain analysis; Karhunen-Loeve transform; colored noise; covariance matrices; generalized subspace approach; matrix diagonalization; multi-talker babble; nonunitary transform; prewhitening; signal estimation; spectral domain constraints; speech enhancement; speech-shaped noise; time-domain constraints; Colored noise; Covariance matrix; Eigenvalues and eigenfunctions; Karhunen-Loeve transforms; Noise reduction; Noise shaping; Signal processing; Speech enhancement; Time domain analysis; White noise;
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
DOI :
10.1109/TSA.2003.814458