We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly in the time domain, permitting the integrated modelling of phase information and being able to take large temporal contexts into account. Our experiments show that the proposed method improves several metrics, namely PESQ, CSIG, CBAK, COVL and SSNR, over the state-of-the-art with respect to the speech enhancement task on the Voice Bank corpus (VCTK) dataset. We find that a reduced number of hidden layers is sufficient for speech enhancement in comparison to the original system designed for singing voice separation in music. We see this initial result as an encouraging signal to further explore speech enhancement in the time-domain, both as an end in itself and as a pre-processing step to speech recognition systems.

研究了 Wave-U-Net 结构在语音增强中的应用，发现其在时域直接建模可以考虑大的时间上下文信息的特点下，可以在 Voice Bank corpus（VCTK）数据集上的语音增强任务中提高 PESQ、CSIG、CBAK、COVL 和 SSNR 多个指标，相比于其原始的音乐中唱声分离系统而言，基于少量隐藏层的结构更适合语音增强，该结果为进一步探索语音增强在时域中的应用提供了鼓舞人心的信号，并可以作为语音识别系统的预处理步骤。

基于Wave-U-Net的语音增强改进