A variant of SWEMDH technique based on variational mode decomposition for speech enhancement

2021 ◽  
Vol 25 (3) ◽  
pp. 299-308
Author(s):  
Poovarasan Selvaraj ◽  
E. Chandra
Keyword(s):  
White Noise ◽  
Speech Enhancement ◽  
Speech Signal ◽  
High Frequency ◽  
Hurst Exponent ◽  
Sliding Window ◽  
Variational Mode Decomposition ◽  
Vocal Signal ◽  
Mode Decomposition ◽  
Vocal Signals

In Speech Enhancement (SE) techniques, the major challenging task is to suppress non-stationary noises including white noise in real-time application scenarios. Many techniques have been developed for enhancing the vocal signals; however, those were not effective for suppressing non-stationary noises very well. Also, those have high time and resource consumption. As a result, Sliding Window Empirical Mode Decomposition and Hurst (SWEMDH)-based SE method where the speech signal was decomposed into Intrinsic Mode Functions (IMFs) based on the sliding window and the noise factor in each IMF was chosen based on the Hurst exponent data. Also, the least corrupted IMFs were utilized to restore the vocal signal. However, this technique was not suitable for white noise scenarios. Therefore in this paper, a Variant of Variational Mode Decomposition (VVMD) with SWEMDH technique is proposed to reduce the complexity in real-time applications. The key objective of this proposed SWEMD-VVMDH technique is to decide the IMFs based on Hurst exponent and then apply the VVMD technique to suppress both low- and high-frequency noisy factors from the vocal signals. Originally, the noisy vocal signal is decomposed into many IMFs using SWEMDH technique. Then, Hurst exponent is computed to decide the IMFs with low-frequency noisy factors and Narrow-Band Components (NBC) is computed to decide the IMFs with high-frequency noisy factors. Moreover, VVMD is applied on the addition of all chosen IMF to remove both low- and high-frequency noisy factors. Thus, the speech signal quality is improved under non-stationary noises including additive white Gaussian noise. Finally, the experimental outcomes demonstrate the significant speech signal improvement under both non-stationary and white noise surroundings.

White noise attenuation of seismic trace by integrating variational mode decomposition with convolutional neural network

Geophysics ◽  
2019 ◽  
Vol 84 (5) ◽  
pp. V307-V317 ◽  
Author(s):  
Hao Wu ◽  
Bo Zhang ◽  
Tengfei Lin ◽  
Fangyu Li ◽  
Naihao Liu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
White Noise ◽  
Seismic Data ◽  
Prior Information ◽  
Training Procedure ◽  
Noise Attenuation ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Mode Decomposition

Seismic noise attenuation is an important step in seismic data processing. Most noise attenuation algorithms are based on the analysis of time-frequency characteristics of the seismic data and noise. We have aimed to attenuate white noise of seismic data using the convolutional neural network (CNN). Traditional CNN-based noise attenuation algorithms need prior information (the “clean” seismic data or the noise contained in the seismic) in the training process. However, it is difficult to obtain such prior information in practice. We assume that the white noise contained in the seismic data can be simulated by a sufficient number of user-generated white noise realizations. We then attenuate the seismic white noise using the modified denoising CNN (MDnCNN). The MDnCNN does not need prior clean seismic data nor pure noise in the training procedure. To accurately and efficiently learn the features of seismic data and band-limited noise at different frequency bandwidths, we first decomposed the seismic data into several intrinsic mode functions (IMFs) using variational mode decomposition and then apply our denoising process to the IMFs. We use synthetic and field data examples to illustrate the robustness and superiority of our method over the traditional methods. The experiments demonstrate that our method can not only attenuate most of the white noise but it also rejects the migration artifacts.

Locally Adaptive Wavelet Thresholding for Speech Enhancement

2013 ◽  
Vol 380-384 ◽  
pp. 3618-3622
Author(s):  
Kang Liu ◽  
Jian Zheng Cheng ◽  
Li Cheng
Keyword(s):  
White Noise ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Bayesian Framework ◽  
Threshold Function ◽  
Wavelet Thresholding ◽  
Wavelet Coefficients ◽  
Edge Preservation ◽  
Adaptive Wavelet ◽  
Locally Adaptive

There are strong dependencies between wavelet coefficients of speech signal,in this article,based on that,a new corresponding nonlinear threshold function derived in Bayesian framework is proposed to decrease the effect of the ambient noise.Analysis of the data shows the effectiveness of the proposed method that it removes white noise more effectually and gets better edge preservation.

Improved variational mode decomposition method for vibration signal processing of flood discharge structure

2021 ◽  
pp. 107754632110161
Author(s):  
Huokun Li ◽  
Gang Wang ◽  
Bowen Wei ◽  
Hanyue Liu ◽  
Wei Huang
Keyword(s):  
High Frequency ◽  
Decomposition Method ◽  
Vibration Signal ◽  
Structural Vibration ◽  
Variational Mode Decomposition ◽  
Flood Discharge ◽  
Mode Decomposition ◽  
Discharge Structure ◽  
Frequency Components ◽  
Structure Vibration

It is crucial for flood discharge structure vibration safety evaluations to filter low-frequency noise, separate dense-frequency components and obtain high-frequency component accurately from vibration signals. Variational mode decomposition, a novel signal adaptive decomposition method, effectively processes flood discharge structures. However, the mode number and quadratic penalty item uncertainty in variational mode decomposition directly affects the vibration signal decomposition. Therefore, an improved variational mode decomposition method for vibration signal processing is proposed in this study. The proposed method adaptively determines the mode number based on singular entropy and frequency stability to completely separate the structural vibration components (including dense-frequency components and high-frequency components) and noise components from the vibration signal. Next, an objective quadratic penalty item function based on sample entropy and mutual information is proposed to quantify the mode mixing between the structural vibration components. Finally, a particle swarm optimisation algorithm based on beetle antenna search is proposed to optimise the quadratic penalty item, which overcomes the shortcomings of traditional algorithms and suppresses the mode mixing between the structural vibration components. The validity and feasibility of the proposed method was verified by the simulation signal and was applied to a sluice prototype project. The results showed that the method effectively filtered noise, greatly improved the vibration response signal-to-noise ratio and obtained the structural vibration component time history signal, which provides a foundation for flood discharge structure vibration safety evaluation and health monitoring.

scholarly journals Robust Estimation of Arrival Time of Complex Noisy Partial Discharge Pulse in Power Cables Based on Adaptive Variational Mode Decomposition

2020 ◽  
Vol 10 (5) ◽  
pp. 1641
Author(s):  
Kang Sun ◽  
Tong Wu ◽  
Xinwei Li ◽  
Jing Zhang
Keyword(s):  
White Noise ◽  
Arrival Time ◽  
Partial Discharge ◽  
Low Frequency ◽  
Discrete Fourier Transformation ◽  
Accurate Estimation ◽  
Narrowband Interference ◽  
Variational Mode Decomposition ◽  
Adaptive Wavelet ◽  
Mode Decomposition

Periodic narrowband signals and white noise are the main interferences in online detection and localization of cable partial discharge (PD), however, existing research has always focused on the white noise suppression only, which is not in line with the actual scene. A novel de-noising method for effectively extracting random PD pulse from complex and strong interferences is proposed in this paper and applied to PD localization. Firstly, an improved adaptive variational mode decomposition (AVMD) is used to decompose periodic narrowband interference, white noise, and PD signal into different intrinsic mode. According to the characteristic that the power of intrinsic mode component of periodic narrowband interference in the discrete Fourier transformation (DFT) power spectrum is much larger than that of PD and white noise, the periodic narrowband is removed out. In order to effectively filter out white noise, a scale adaptive wavelet packet decomposition method based on correlation coefficient is proposed, which decomposes the signal into high, middle, and low-frequency components. The components with low frequency, small amplitude are removed out as the white noise interference according to the threshold method, and the residual is the de-noising PD signal. Experimental results show that the proposed method can robustly suppress the interference of periodic narrowband signal and white noise, and effectively preserve the essential characteristics of the real PD signal. In the multi-sensor travelling wave based localization system of cable PD source using time-varying kurtosis, accurate estimation of first arrival time of PD pulse can be achieved by the de-noising results.

scholarly journals Single Channel Speech Enhancement Using Adaptive Soft-Thresholding with Bivariate EMD

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Md. Ekramul Hamid ◽  
Md. Khademul Islam Molla ◽  
Xin Dang ◽  
Takayoshi Nakai
Keyword(s):  
Speech Enhancement ◽  
Speech Signal ◽  
Single Channel ◽  
Complex Signal ◽  
Intrinsic Mode Functions ◽  
Noisy Speech ◽  
Mode Decomposition ◽  
Data Adaptive ◽  
Improved Performance ◽  
Short Time

This paper presents a novel data adaptive thresholding approach to single channel speech enhancement. The noisy speech signal and fractional Gaussian noise (fGn) are combined to produce the complex signal. The fGn is generated using the noise variance roughly estimated from the noisy speech signal. Bivariate empirical mode decomposition (bEMD) is employed to decompose the complex signal into a finite number of complex-valued intrinsic mode functions (IMFs). The real and imaginary parts of the IMFs represent the IMFs of observed speech and fGn, respectively. Each IMF is divided into short time frames for local processing. The variance of IMF of fGn calculated within a frame is used as the reference term to classify corresponding noisy speech frame into noise and signal dominant frames. Only the noise dominant frames are soft-thresholded to reduce the noise effects. Then, all the frames as well as IMFs of speech are combined, yielding the enhanced speech signal. The experimental results show the improved performance of the proposed algorithm compared to the recently reported methods.

Sign in / Sign up

Export Citation Format

Share Document