Abstract | ||
---|---|---|
This paper studies the statistical properties of the gain functions, which are often used for two-channel post-filtering (TC-PF) algorithms. We reveal that the smoothing factor has a significant impact on both noise reduction and musical noise. When the smoothing factor increases, noise reduction can be improved and musical noise can be reduced simultaneously. However, the smoothing factor could not be too close to one because the system can only be assumed to be time-invariant for short durations. To solve this problem, this paper proposes an adaptive smoothing scheme by detecting the sudden change of the system. Moreover, the residual noise floor is adaptively chosen based on the structure of the noise power spectral density (NPSD) to further suppress the tonal noise components. Experimental results show the better performance of the proposed algorithm in terms of the segmental signal-to-noise-ratio (SNR) and the PESQ improvements. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5946839 | 2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING |
Keywords | Field | DocType |
power spectral density,speech,statistical analysis,pesq,noise,noise reduction,signal to noise ratio,snr,sensors | Value noise,Noise measurement,Noise (signal processing),Computer science,Salt-and-pepper noise,Artificial intelligence,Noise power,Pattern recognition,Algorithm,Speech recognition,Smoothing,Gaussian noise,Gradient noise | Conference |
Volume | Issue | ISSN |
null | null | 1520-6149 |
Citations | PageRank | References |
5 | 0.52 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chengshi Zheng | 1 | 32 | 11.66 |
Yi Zhou | 2 | 15 | 9.83 |
Xiaohu Hu | 3 | 8 | 1.60 |
Xiaodong Li | 4 | 48 | 14.00 |