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. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/TSA.2003.814458 | IEEE Transactions on Speech and Audio Processing |
Keywords | Field | DocType |
generalized subspace approach,signal estimation,multi-talker babble,parameter estimation,karhunen-loeve transforms,karhunen-loeve transform,covariance matrices,spectral-domain analysis,acoustic noise,nonunitary transform,random noise,time-domain analysis,colored noise,speech-shaped noise,matrix diagonalization,prewhitening,speech enhancement,spectral domain constraints,time-domain constraints,white noise,covariance matrix,noise reduction,time domain,signal processing,karhunen loeve transform,noise shaping,indexing terms | Noise,Value noise,Colors of noise,Noise measurement,Subspace topology,Computer science,White noise,Speech recognition,Signal subspace,Gradient noise | Journal |
Volume | Issue | ISSN |
11 | 4 | 1063-6676 |
Citations | PageRank | References |
126 | 6.27 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Y. Hu | 1 | 1098 | 69.42 |
Philipos C. Loizou | 2 | 991 | 71.00 |