Performance analysis of adaptive variational mode decomposition approach for speech enhancement

Speech enhancement is an important pre-processing task in the area of speech processing research. Many techniques have been applied in this area since four/five decades. With progressive research it occupies a special position in various fields like engineering, medicine, society and security. Adaptive algorithms found effective for such cases and are utilized in this problem. The work is based on decomposition method using variational mode decomposition (VMD) technique, where the decomposed components signify the frequency characteristics of the signal. Since Wiener filtering is used in VMD inherently, it is modified with the least mean squares (LMS) adaptive algorithm for good accuracy and adaptability in this work. Different noises like Babble noise, Street noise, and Exhibition noise are considered and the corresponding signals are decomposed into five intrinsic mode functions (IMFs). Basically, the lower modes are of high frequency and noisy; whereas the higher mode IMFs contain the low and medium frequency components and are considered as the enhanced signal. The results of the proposed algorithm are found excellent as compared to earlier techniques. The resultant wave forms are visually observed and the sound is verified for audible range. Also different measuring parameters are considered for its performance measure. It is measured in terms of signal-to-noise ratio (SNR), segmental signal to noise ratio (SegSNR), perceptual evaluation of speech quality (PESQ) and log spectral distance (LSD). The technique is verified with standard database NOIZEUS for 0, 5, 10, 15 dB respectively and also in real world case.

[1]  Yi Hu,et al.  Evaluation of Objective Quality Measures for Speech Enhancement , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[2]  John J. Soraghan,et al.  EMD-Based Filtering (EMDF) of Low-Frequency Noise for Speech Enhancement , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  S. El-Rabaie,et al.  Speech enhancement with an adaptive Wiener filter , 2013, International Journal of Speech Technology.

[4]  Bernard Widrow,et al.  Adaptive Signal Processing edited by Bernard Widrow and Samuel D. Stearns , 1986 .

[5]  Saad Bouguezel,et al.  A new pre-whitening transform domain LMS algorithm and its application to speech denoising , 2017, Signal Process..

[6]  Leonardo Zao,et al.  Speech Enhancement with EMD and Hurst-Based Mode Selection , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[7]  Ram Bilas Pachori,et al.  Speech enhancement based on mEMD-VMD method , 2017 .

[8]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[9]  Navneet Upadhyay,et al.  Single Channel Speech Enhancement: Using Wiener Filtering with Recursive Noise Estimation , 2015, IHCI.

[10]  Ming Li,et al.  Variational mode decomposition denoising combined the detrended fluctuation analysis , 2016, Signal Process..

[11]  Sanaz Seyedin,et al.  A novel speech enhancement method by learnable sparse and low-rank decomposition and domain adaptation , 2016, Speech Commun..

[12]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[13]  S. Hahn.  Hilbert Transforms in Signal Processing , 1996 .

[14]  Abdel-Ouahab Boudraa,et al.  Voiced/unvoiced speech classification-based adaptive filtering of decomposed empirical modes for speech enhancement , 2016, IET Signal Process..

[15]  Juan Carlos,et al.  Review of "Discrete-Time Speech Signal Processing - Principles and Practice", by Thomas Quatieri, Prentice-Hall, 2001 , 2003 .

[16]  Mihir Narayan Mohanty,et al.  Performance Analysis of Adaptive Algorithms for Speech Enhancement Applications , 2016 .

[17]  Sabyasachi Patra,et al.  Application of Variational Mode Decomposition on Speech Enhancement , 2017, RICE.

[18]  Abdel-Ouahab Boudraa,et al.  Speech enhancement using empirical mode decomposition and the Teager-Kaiser energy operator. , 2014, The Journal of the Acoustical Society of America.

[19]  A. Sreenivasa Murthy,et al.  Comparison of Speech Enhancement Algorithms , 2016 .

[20]  Yanxue Wang,et al.  Filter bank property of variational mode decomposition and its applications , 2016, Signal Process..

[21]  Ram Bilas Pachori,et al.  Determination of instantaneous fundamental frequency of speech signals using variational mode decomposition , 2017, Comput. Electr. Eng..

[22]  Mihir Narayan Mohanty,et al.  Comparative Analysis of EMD and VMD Algorithm in Speech Enhancement , 2017, Int. J. Nat. Comput. Res..

[23]  Philipos C. Loizou,et al.  Speech Enhancement: Theory and Practice, Second Edition , 2013 .

[24]  K. P. Soman,et al.  A VMD Based Approach for Speech Enhancement , 2015, SIRS.

[25]  Mohammad Bilal Malik,et al.  State-space recursive least squares: Part II , 2004, Signal Process..

[26]  Philipos C. Loizou,et al.  Speech Enhancement: Theory and Practice , 2007 .

[27]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.