Abstract | ||
---|---|---|
A new perceptually motivated approach is proposed in this paper for enhancement of speech corrupted by colored noise. The proposed approach takes into account the frequency masking properties of the human auditory system and reduces the perceptual effect of the residual noise. This new perceptual method is incorporated into a frequency-domain speech enhancement method and a subspace-based speech enhancement method. A better power spectrum/autocorrelation function estimator was also developed to improve the performance of the proposed algorithms. Objective measures and informal listening tests demonstrated significant improvements over other methods when tested with TIMIT sentences corrupted by various types of colored noise. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1109/TSA.2003.815936 | IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING |
Keywords | Field | DocType |
multitaper power spectrum estimation, multiwindow covariance matrix estimation, perceptual weighting, spectral subtraction method, speech enhancement, subspace method | Noise reduction,Speech enhancement,TIMIT,Speech processing,Speech synthesis,Colors of noise,Speech coding,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Estimation theory | Journal |
Volume | Issue | ISSN |
11 | 5 | 1063-6676 |
Citations | PageRank | References |
33 | 1.91 | 16 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Y. Hu | 1 | 1098 | 69.42 |
Philipos C. Loizou | 2 | 991 | 71.00 |