本文提出一种利用双解码卷积循环网 络(Dual-decoder Convolutional Recurrent Network,DCRN)代替 FxLMS(Filtered-x Least Mean Square)算法的有源噪声控制方法,考虑到相位信息在有源噪声控制(Active Noise Control,ANC)中的重要性,DCRN 网络的输入特征为噪声信号的复数频谱(包括实部谱和虚部谱).网络结构中,采用编码模块从噪声复数频谱中提取特征,利用双解码模块分别估计网络输出的实部谱和虚部谱,采用参数共享机制和组策略以降低训练参数的数量并提高网络的学习能力和泛化能力.特别是针对风噪声,选用新的损失函数以及对训练数据进行正则化处理以提升 DCRN 的性能.实验结果表明,DCRN 方法在仿真环境与有源降噪耳机环境下对一般噪声和风噪声都表现出良好的降噪性能和鲁棒性.
Active control of wind noise with dual-decoder convolutional recurrent network
Here,an Active Noise Control(ANC)approach is proposed which replaces Filtered-x Least Mean Square(FxLMS)algorithm with Dual-decoder Convolutional Recurrent Network(DCRN).Due to the importance of phase information in ANC,the input feature of DCRN is the complex spectrogram of the noise signal(including real and imaginary spectrograms).In the network structure,a coding module is used to extract features from the noise complex spectrograms,and a dual-decoder module is used to estimate the real and imaginary spectrograms of the network output.Parameter sharing mechanism and group strategy are adopted to reduce the number of training pa-rameters and improve the learning ability and generalization performance.Especially for wind noise,a new loss func-tion is adopted and the training data are regularized to improve the performance of DCRN.Experiments in both simu-lation and ANC headphone environments show that the DCRN approach exhibits good noise reduction performance and robustness for both general noise and wind noise.
dual-decoder convolutional recurrent network(DCRN)active noise control(ANC)filtered-x least mean square(FxLMS)algorithmcomplex spectrogram
万方数据
维普
