Volume 7, Issue 3, June 2019, Page: 92-98
Improved Wiener Filter Algorithm for Speech Enhancement
Zhao Yanlei, Department of Science and Technology for Opto-electronic Information, Yantai University, Yantai, China
Ou Shifeng, Department of Science and Technology for Opto-electronic Information, Yantai University, Yantai, China
Gao Ying, Department of Science and Technology for Opto-electronic Information, Yantai University, Yantai, China
Received: Nov. 18, 2019;       Published: Nov. 18, 2019
DOI: 10.11648/j.acis.20190703.13      View  23      Downloads  12
Abstract
Most of the existing speech enhancement algorithms are aimed at improving the quality of speech, and the algorithms that can improve the speech intelligibility effectively are rare. Speech intelligibility has been found to improve listening comfort and it is generally related to the distortion of the speech signal closely. Studies have assessed the impact of speech distortion introduced by gain functions and shown that one of the main reasons that existing algorithms cannot improve speech intelligibility is because they allow amplification distortions more than 6dB. Therefore, these distortions of the enhanced amplitude spectrum should be corrected to improve the speech intelligibility. The early research by Loizou et al. obtained the experimental results on the ideal state and we are unable to use it in reality because there is no clean speech in reality. In this paper, we modify the method proposed by Loizou et al. and select the estimated speech under two hypothetical conditions to verify the improvement of the speech intelligibility. The short-term objective intelligibility value verifies the improvement of speech intelligibility as the improved algorithm of speech intelligibility is applied to reality successfully.
Keywords
Speech Intelligibility, Amplification Distortion, Short-Term Objective Intelligibility Value
To cite this article
Zhao Yanlei, Ou Shifeng, Gao Ying, Improved Wiener Filter Algorithm for Speech Enhancement, Automation, Control and Intelligent Systems. Vol. 7, No. 3, 2019, pp. 92-98. doi: 10.11648/j.acis.20190703.13
Reference
[1]
G. Kim and P. Loizou, “Gain-induced speech distortions and the absence of intelligibility benefit with existing noise-reduction algorithms,” Acoustical Society of America, vol. 130, 2011, pp. 1581-1596.
[2]
T. Baer, B. Moore, and S. Gatehouse, “Spectral contrast enhancement of speech in noise for listeners with sensorineural hearing impairment: Effects on intelligibility, quality and response times,” J. Rehab. Res. Dev. Vol (30), 1993, pp. 49–72.
[3]
J. Alcantar, B. Moore, V. Kuhnel, and S. Launer, “Evaluation of the noise reduction system in a commercial digital hearing aid,” Int. J. Audiol, vol. (42), 2003, pp. 34–42.
[4]
Bai Haichuan, Ge Fengpei and Yan Yonghong, “DNN-based speech enhancement using soft audible noise masking for wind noise reduction,”Merging Technologies and Applications, vol. 15 (9), 2018, pp. 235-243.
[5]
F. Chen and P. Loizou, “Impact of SNR and gain-function over-and under-estimation on speech intelligibility,” Speech Communication, vol. 54, 2012, pp. 272-281.
[6]
P. Loizou, Speech Enhancement: Theory and Practice. Boca Raton: Florida, CRC Press LLC, 2007, pp. 97-99.
[7]
P. Loizou and G. Kim, “Reasons why current speech- enhancement algorithms do not improve speech intelligibility and suggested solutions,” IEEE Trans. Audio, Speech, Lang. Process, vol. 19 (1), 2011, pp. 47-56.
[8]
L. Yang and P. Loizou,“Estimators of the Magnitude-Squared Spectrum and Methods for Incorporating SNR Uncertainty”, Senior Member, IEEE, vol. 19 (5), 2011, pp1123-1137.
[9]
R. Martin, “Noise Power Spectral Density Estimation based on Optimal Smoothing and Minimum Statistics,” IEEE Transactions on Speech and Audio Processing, vol. 9(5), 2001, pp. 504-512.
[10]
P. J. Wolfe and S. J. Godsill, “Efficient alternatives to Ephraim and Malah suppression rule for audio signal enhancement,” EURASIP J. Appl. Signal Process, vol. 10, 2003, pp. 1043–1051.
[11]
Guo Lihua and Ma Jianfen, “Improved Wiener filtering speech enhancement algorithm with high intelligibility,” Computer applications and software, vol. 31 (11), 2014, pp. 155-157.
[12]
Chen Chen, Gao Ying and Liu Wei. “Comparative Analysis of Priori SNR Estimation Algorithms in Single Channel Speech Enhancement,” Circuits and Systems, vol. 7 (2), 2018, pp. 25-35.
[13]
IEEE Subcommittee, “IEEE Recommended Practice for Speech Quality Measurements,” IEEE Trans. Audio and Electro acoustics, vol. 17 (3), 1969, pp. 225-246.
[14]
Y. Lu and P. Loizou, “Speech enhancement by combining statistical estimators of speech and noise,” in Proceedings of IEEE International Conference on Acoustics, Speech, Signal Processing, 2010, pp. 4754–4757.
[15]
Y. Hu and P. Loizou, “Subjective comparison and evaluation of speech enhancement algorithms,” Speech Commun, 2007, vol. 49, pp. 588–601.
[16]
F. Gelderblom, T. Tronstad and E. Viggen, “Subjective Evaluation of a Noise-Reduced Training Target for Deep Neural Network-Based Speech Enhancement,” IEEE/ACM Transactions on Audio Speech and Language Processing, vol. 27 (3), 2019, pp. 583-594.
[17]
C. Tan and B. Moore, “Perception of nonlinear distortion by hearing-impaired people,” Int. J. Audiol. 2008, vol. 47, pp. 246–256.
[18]
S. Rangachari and P. Loizou, “A noise-estimation algorithm forhighly non-stationary environments,” Speech Commun. 2006, vol. 48, pp. 220–231.
[19]
Y. Hu and P. Loizou, “A comparative intelligibility study of single-microphone noise reduction algorithms,” J. Acoust. Soc. Am, 2007, vol. 122, pp. 1777–1786.
[20]
I. Cohen, “Noise Estimation by Minima Controlled Recursive Averaging for Robust Speech Enhancement”, IEEE Signal Processing Letter, vol. 9 (1), 2002, pp. 12-15.
[21]
E. Nemer, and W. Leblanc, “Single-microphone Wind Noise Reduction by Adaptive Postfiltering,” IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA2009), 2009, pp. 177-180.
Browse journals by subject