|
Comparative Analysis Of Various Noise Types Using Empirical Mode Decomposition Based Hurst Exponent Techniques
[Full Text]
AUTHOR(S)
Poovarasan Selvaraj, Dr.Chandra Eswaran
KEYWORDS
Empirical mode decomposition, Sifting Process, Hurst Exponent, Various types of Noise, EMDH.
ABSTRACT
Generally, Speech enhancement aims to develop a speech quality and intelligibility of a noise corrupted speech signal by using various Speech Enhancement techniques. Speech enhancement approach, Empirical Mode Decomposition and Hurst-based (EMDH) approach was proposed for signals corrupted by non-stationary acoustic noises. In this technique, Hurst exponent statistics was adopted for identifying and selecting the set of Intrinsic Mode Functions (IMF) that are most affected by the noise components. The results show that the EMDH improves speech quality were evaluated by the performance matrices of Cross Correlation, Mean Square Error, Peak Signal to Noise Ratio and the perceptual evaluation of speech quality (PESQ). An experimental study was also done on various types of noise added in clean speech like Gaussian White Noise, Random Noise and Colored Noise.
REFERENCES
[1]. Alugonda Rajani et.al “A Review on Various Speech Enhancement Techniques” International Journal of Advanced Research in Computer and Communication Engineering, Vol. 5, Issue 8, August 2016
[2]. Navneet Upadhyay et.al “Single Channel Speech Enhancement: using Wiener Filtering with Recursive Noise Estimation” Procedia Computer Science 84 ( 2016 ) 22 – 30
[3]. L. Zão and R. Coelho, “Colored noise based multicondition training technique for robust speaker identification,” IEEE Signal Process. Lett., vol. 18, no. 11, pp. 675–678, Nov. 2011
[4]. Chatlani, N., & Soraghan, J. J. (2012). EMD-based filtering (EMDF) of low-frequency noise for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 20(4), 1158-1166.
[5]. Khaldi, K., Boudraa, A. O., & Komaty, A. (2014). Speech enhancement using empirical mode decomposition and the Teager–Kaiser energy operator. The Journal of the Acoustical Society of America, 135(1), 451-459.
[6]. Dwijayanti, S., Yamamori, K., & Miyoshi, M. (2018). Enhancement of speech dynamics for voice activity detection using DNN. EURASIP Journal on Audio, Speech, and Music Processing, 2018(1), 10.
[7]. Ghahabi, O., Zhou, W., & Fischer, V. (2018). A Robust Voice Activity Detection for Real-Time Automatic Speech Recognition. In Proceedings of ESSV 2018, Ulm 2018.
[8]. Chatlani, N., & Soraghan, J. J. (2012). EMD-based filtering (EMDF) of low-frequency noise for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 20(4), 1158-1166
[9]. Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time–frequency weighted noisy speech. IEEE Transactions on Audio, Speech, and Language Processing, 19(7), 2125-2136.
[10]. Mai, V. K., Pastor, D., Aïssa-El-Bey, A., & Le-Bidan, R. (2015). Robust estimation of non-stationary noise power spectrum for speech enhancement. IEEE Transactions on Audio, Speech, and Language Processing, 23(4), 670-682.
[11]. Md. Ekramul Hamid et.al “ Speech Enhancement Using EMD Based Adaptive Soft-Thresholding (EMD-ADT)”International Journal of Signal Processing, Image Processing and Pattern Recognition Vol. 5, No. 2, June, 2012.
|
