Abstract | ||
---|---|---|
Most speech enhancement techniques do not perform very well in correlated or colored noise, as they assume that noise and speech are not correlated. In this paper, we propose a method, based on spectral subtraction, which takes into account possible correlation between noise and speech. Objective measures showed that the proposed method outperformed the power spectral subtraction method resulting in better speech quality and reduced levels of musical noise. Further enhancements in speech quality were obtained by applying a perceptual weighting function (estimated using a psychoacoustics model) that was designed to minimize noise distortion |
Year | DOI | Venue |
---|---|---|
2001 | 10.1109/ICASSP.2001.940921 | ICASSP |
Keywords | Field | DocType |
perceptual weighting filter,psychoacoustics model,perceptual weighting function,objective measures,spectral subtraction,acoustic noise,cross-correlation technique,musical noise,colored noise,filtering theory,speech quality,speech enhancement,correlated noise,correlation methods,noise distortion minimization,cross correlation,noise measurement,explosives,noise reduction,weight function | Noise,Speech enhancement,Value noise,Colors of noise,Noise measurement,Pattern recognition,Computer science,Salt-and-pepper noise,Speech recognition,Artificial intelligence,Noise,Gradient noise | Conference |
Volume | ISSN | ISBN |
1 | 1520-6149 | 0-7803-7041-4 |
Citations | PageRank | References |
3 | 0.64 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Y. Hu | 1 | 1098 | 69.42 |
Mukul Bhatnagar | 2 | 3 | 0.64 |
Philipos C. Loizou | 3 | 991 | 71.00 |