2 papers
eess.AS2025
A Universal Harmonic Discriminator for High-quality GAN-based Vocoder
Nan Xu, Zhaolong Huang, Xiao Zeng
With the emergence of GAN-based vocoders, the discriminator, as a crucial component, has been developed recently. In our work, we focus on improving the time-frequency based discri…
eess.AS2025
MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement
Nan Xu, Zhaolong Huang, Xiaonan Zhi
With the development of deep learning, speech enhancement has been greatly optimized in terms of speech quality. Previous methods typically focus on the discriminative supervised l…