In-Vehicle Environment Noise Speech Enhancement Using Lightweight Wave-U-Net

With the rapid advancement of AI technology, speech recognition has also advanced quickly. In recent years, speech-related technologies have been widely implemented in the automotive industry. However, in-vehicle environment noise inhibits the recognition rate, resulting in poor speech recognition performance. Numerous speech enhancement methods have been proposed to mitigate this performance degradation. Filter-based methodologies have been used to remove existing vehicle environment noise; however, they remove only limited noise. In addition, there is the constraint that there are limits to the size of models that can be mounted inside a vehicle. Therefore, making the model lighter while increasing speech quality in a vehicle environment is an essential factor. This study proposes a Wave-U-Net with a depthwise-separable convolution to overcome these limitations. We built various convolutional blocks using the Wave-U-Net model as a baseline to analyze the results, and we designed the network by adding squeeze-and-excitation network to improve performance without significantly increasing the parameters. The experimental results show how much noise is lost through spectrogram visualization, and that the proposed model improves performance in eliminating noise compared with conventional methods.