基于注意力机制的卷积循环网络语音降噪

不同噪声在频谱上具有不同的特性,为了解决卷积神经网络对含有不同噪声的语音降噪的局限性,通过引入通道注意力机制作为卷积循环网络的中间层,将卷积层中不同功能的卷积核赋予不同的权重,使模型在训练时能够对输入数据更有针对性的去除噪声部分,从而达到更好的降噪效果。针对含有15种噪声的含噪语音分别应用循环神经网络、卷积循环神经网络等三种模型进行降噪处理,结果表明引入注意力机制的模型相比于其他两种模型,在PESQ和STOI评分上都有所提高,且引入注意力机制的模型能够更好的保留语音的谐波信息。

Speech Denoising Based on Channel Attention Mechanism Using Self-coding Convolutional Loop Network

Different noises have different characteristics in frequency spectrum, in order to solve the limitation of convolutional neural network for speech denoising with different noises, through the introduction of channel attention mechanism as the middle layer of convolution loop network, the convolution kernel of different functions in the convolution layer is given different weights, so that the model can be more targeted to remove the noise part of the input data in training, so as to achieve better denoising effect. For noisy speech with 15 kinds of noise, three models such as recurrent neural network and convolutional recurrent neural network are used for noise reduction, and the results show that the model with attention mechanism can improve the PESQ and STOI scores compared with the other two models, and the model with attention mechanism can better retain the harmonic information of speech.