News

This paper presents a denoising and dereverberation hierarchical neural vocoder (DNR-HiNet) to convert noisy and reverberant acoustic features into a clean speech waveform. We implement it mainly by ...
In this study, a Mel-domain denoising autoencoder and a deep generative vocoder are stacked to form a joint framework for monaural speech enhancement, in which the clean speech waveform is ...