Speech Enhancement in Short-Wave Channel Based on Empirical Mode Decomposition
A novel speech enhancement method based on empirical mode decomposition is proposed. The method is a fully data driven approach. Noisy speech signal is decomposed adaptively into oscillatory components called Intrinsic Mode Functions (IMFs) using a process called sifting. The empirical mode decomposition denoising involves thresholding each IMFs. A nonlinear function is introduced for amplitude thresholding. And then reconstructs the estimated speech signal using the processed IMFs. The experimental results show significant improvement in output SNR and quality as compared to recently reported results.
KeywordsSpeech Signal Empirical Mode Decomposition Minimum Mean Square Error Speech Enhancement Clean Speech
Unable to display preview. Download preview PDF.
- 3.Zheng, W.T., Cao, Z.H.: Speech enhancement based on MMSE-STSA estimation and residual noise reduction. In: 1991 IEEE Region 10 International Conference on EC3-Energy, Computer, Communication and Control Systems, vol. 3, pp. 265–268 (1991)Google Scholar
- 4.Zhibin, L., Naiping, X.: Speech enhancement based on minimum mean-square error short-time spectral estimation and its realization. In: IEEE International conference on intelligent processing system, vol. 28, pp. 1794–1797 (1997)Google Scholar
- 7.He, C., Zweig, Z.: Adaptive two-band spectral subtraction with multi-window spectral estimation. In: ICASSP, vol. 2, pp. 793–796 (1999)Google Scholar
- 10.Huang, W., Shen, Z., Huang, N.E., Fung: Nonlinear Indicial Response of Complex Nonstationary Oscillations as Pulmonary Pretension Responding to Step Hypoxia. Proc. Natl. Acad. Sci, USA 96, 1833–1839 (1999)Google Scholar