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 ps...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.展开更多
为了提高建筑物变形监测中的预测精度,降低噪声对变形预测的影响,本文在局部均值分解(Local Mean Decomposition,LMD)方法的基础上,引入小波阈值去噪方法,提出一种新的LMD-小波阈值去噪方法。该方法实现信号去噪,步骤为:首先是通过LMD...为了提高建筑物变形监测中的预测精度,降低噪声对变形预测的影响,本文在局部均值分解(Local Mean Decomposition,LMD)方法的基础上,引入小波阈值去噪方法,提出一种新的LMD-小波阈值去噪方法。该方法实现信号去噪,步骤为:首先是通过LMD将信号分解为若干个乘积函数(Product Function,PF)以及余量,通过消除趋势波动分析方法计算H指数的方式得到PF分量中高频噪声分量与低频有用信号分量;其次是通过小波阈值去噪方法对高频分量进行进一步降噪,得到有用信息,并重构降噪后信号、低频分量以及余量得到降噪后信号;最后建立RBF神经网络模型对降噪后数据进行建模与预测。使用建筑物监测数据对本文提出方法进行验证,结果表明:本文方法较LMD方法、经验模态分解(Empirical Mode Decomposition,EMD)方法的降噪效果更好,降噪后数据预测精度更高,可在工程类监测项目中进一步应用。展开更多
基金partially supported by the National Natural Science Foundation of China (Nos.11590772, 11590770)the Pre-research Project for Equipment of General Information System (No.JZX2017-0994/Y306)
文摘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.
