DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction

This paper presents a deep neural network(DNN)-based speech enhancement algorithm based on the soft audible noise masking for the single-channel wind noise reduction. To reduce the low-frequency residual noise, the psychoacoustic model is adopted to calculate the masking threshold from the estimated clean speech spectrum. The gain for noise suppression is obtained based on soft audible noise masking by comparing the estimated wind noise spectrum with the masking threshold. To deal with the abruptly time-varying noisy signals, two separate DNN models are utilized to estimate the spectra of clean speech and wind noise components. Experimental results on the subjective and objective quality tests show that the proposed algorithm achieves the better performance compared with the conventional DNN-based wind noise reduction method.

Experimental and Numerical Study of Wind Noise Caused by Cowl Area on Volvo XC60

This paper presents a detailed experimental and numerical study of aerodynamically produced noise which occurs due to turbulent structures created by the cowl cavity and side mirror. Measurements were carried out at Volvo aerodynamical wind tunnel on a Volvo XC60 production model. The configurations considered here are： side mirror On/Off with the cowl cavity open/closed. The results of exterior sound source mapping （with the intensity probe placed in the flow stream） have been compared with the results of the measurements inside the car. The contribution of the cowl area to overall wind noise level is measured in terms of AI% （Articulation Index） inside the compartment. It was shown that increase in AI by 2% could be attributed to the cowl generated wind noise. Transient numerical simulations of the turbulent flow around the car have been performed for all configurations. The results of the simulations show similarity to experimental results and give insight to the flow structures around the car.

Wind Turbine Noise Reduction through Blade Retrofitting

This paper outlines a plan for the effective reduction of the audible sound level produced by aerodynamic noise from the power-generating turbine blades. The contribution of aerodynamic noise can be divided into two categories: inflow turbulence and airfoil self-noise. The base model and retrofit blade designs were modeled in SolidWorks. Subsequently, noise prediction simulations were conducted and compared to the base blade model to determine which modification provided the greatest benefit using SolidWorks Flow Simulation. The result of this project is a series of blade retrofit recommendations that produce a more acoustically efficient design and reduce noise complaints while enabling turbines to be placed in locations that require quieter operations.

A method of convolutional neural network based on frequency segmentation for monitoring the state of wind turbine blades

Wind turbine blades are prone to failure due to high tip speed,rain,dust and so on.A surface condition detecting approach based on wind turbine blade aerodynamic noise is proposed.On the experimental measurement data,variational mode decomposition filtering and Mel spectrogram drawing are conducted first.The Mel spectrogram is divided into two halves based on frequency characteristics and then sent into the convolutional neural network.Gaussian white noise is superimposed on the original signal and the output results are assessed based on score coefficients,considering the complexity of the real environment.The surfaces of Wind turbine blades are classified into four types:standard,attachments,polishing,and serrated trailing edge.The proposed method is evaluated and the detection accuracy in complicated background conditions is found to be 99.59%.In addition to support the differentiation of trained models,utilizing proper score coefficients also permit the screening of unknown types.

Noise reduction in LOS wind velocity of Doppler lidar using discrete wavelet analysis

The line of sight (LOS) wind velocity can be determined from the incoherent Doppler lidar backscattering signals. Noise and interference in the measurement greatly degrade the inversion accuracy. In this paper, we apply the discrete wavelet denoising method by using biorthogonal wavelets and adopt a distance-dependent thresholds algorithm to improve the accuracy of wind velocity measurement by incoherent Doppler lidar. The noisy simulation data are processed and compared with the true LOS wind velocity. The results are compared by the evaluation of both the standard deviation and correlation coefficient. The results suggest that wavelet denoising with distance-dependent thresholds can considerably reduce the noise and interfering turbulence for wind lidar measurement.