Performance Analysis of the Wiener Optimal Filtering Noise-Reduction Technique

Abstract:

Noise reduction, which aims at extracting the clean speech from noisy observations, has attracted a considerable amount of research attention over the past several decades. Although many methods have been developed to achieve the goal of noise reduction and signal-to-noise ratio (SNR) improvement, there has been remarkably little theoretical justification of their performance due to the difficulty in quantizing the combinatorial effect between noise reduction and speech distortion. This paper attempts to provide a theoretical analysis on the performance of the Wiener optimal filtering noise-reduction technique. We show that the Wiener optimal linear filter can indeed reduce the level of noise. Most importantly, we prove that the output SNR is always greater than, or at least equal to the input SNR, which reveals that the Wiener optimal linear filtering technique is indeed able to make noisy speech signals cleaner.

• Periodical: Advanced Materials Research (Volumes 816-817)
• Pages: 484-487
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.816-817.484
• Online since: September 2013
• Authors: Lin Xue, Yun Shan Hou
• Keywords: Noise Reduction, SNR, Speech Distortion, Wiener Optimal Filter

References

[1] Habets, Emanuel A. P., Benesty, Jacob. A Two-Stage Beamforming Approach for Noise Reduction and Dereverberation. IEEE Trans. on ASLP, 2013, 21(5): 945-958.

DOI: 10.1109/tasl.2013.2239292

[2] Chen, Jingdong; Benesty, Jacob. On the Time-Domain Widely Linear LCMV Filter for Noise Reduction With a Stereo System. IEEE Trans. on ASLP, 2013, 21(7): 1343-1354.

DOI: 10.1109/tasl.2013.2248719

[3] Gannot, S., Burshtein, D., Weinstein, E. Iterative and sequential Kalman filter-based speech enhancement algorithms. IEEE Trans. on ASLP, 1998, 6 (7): 373–385.

DOI: 10.1109/89.701367

[4] Jingdong Chen; Benesty, J.; Yiteng Huang; Doclo, S. New insights into the noise reduction Wiener filter. IEEE Trans. on ASLP, 2006, 14(4): 1218-1234.

DOI: 10.1109/tsa.2005.860851

[5] Jingdong Chen; Benesty, J.; Yiteng Huang. Study of the Noise-Reduction Problem in the Karhunen–Loève Expansion Domain. IEEE Trans. on ASLP, 2009, 17(4): 787-802.

DOI: 10.1109/tasl.2009.2014793

[6] S. Doclo and M. Moonen. GSVD-based optimal filtering for single and multi-microphone speech enhancement. IEEE Transactions on Signal Processing, 2002, 50(9): 2230–2244.

DOI: 10.1109/tsp.2002.801937

[7] Chen, J., Huang, Y., Benesty, J. Adaptive Signal Processing: Applications to Real-World Problems. Springer, Berlin, Germany, (2003).

[8] Fukunaga, K. Introduction to Statistical Pattern Recognition. Academic, San Diego, CA, USA. (1990).