Please use this identifier to cite or link to this item:
http://nopr.niscpr.res.in/handle/123456789/11640| Title: | Enhancement of noisy speech signal based on variance and modified gain function with PDE preprocessing technique for digital hearing aid |
| Authors: | Deepa, D Shanmugam, A |
| Keywords: | MSE;PDE;SNR;Adaptive threshold;Gain function;Variance |
| Issue Date: | May-2011 |
| Publisher: | NISCAIR-CSIR, India |
| Abstract: | This paper deals with a single-channel speech enhancement algorithm, preprocessed using partial differential equation, used to overcome degradation of noisy speech signals in digital hearing aids. Adaptive threshold is estimated using variance in time index. Gain is modified based on adaptive threshold estimated in frequency bins and used to enhance noisy signal. By proposed method, definite improvement in SNR and reduced MSE can be obtained compared to conventional method. This method provides a greater degree of flexibility and control on noise subtraction levels that reduce artifacts in enhanced speech, resulting in improved speech quality and intelligibility. |
| Page(s): | 332-337 |
| ISSN: | 0975-1084 (Online); 0022-4456 (Print) |
| Appears in Collections: | JSIR Vol.70(05) [May 2011] |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| JSIR 70(5) 332-337.pdf | 107.69 kB | Adobe PDF | View/Open |
Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.