Lightweight End-to-End Speech Enhancement Generative Adversarial Network Using Sinc Convolutions

Lightweight End-to-End Speech Enhancement Generative Adversarial Network Using Sinc Convolutions

Generative adversarial networks (GANs) have recently garnered significant attention for their use in speech enhancement tasks, in which they generally process and reconstruct speech waveforms directly. Existing GANs for speech enhancement rely solely on the convolution operation, which may not accur...

Full description

Bibliographic Details
Main Authors: Lujun Li, Wudamu, Ludwig Kürzinger, Tobias Watzel, Gerhard Rigoll
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Applied Sciences
Subjects:
speech enhancement
generative adversarial networks
Sinc convolution
data augmentation
raw samples
Online Access:https://www.mdpi.com/2076-3417/11/16/7564

Internet

https://www.mdpi.com/2076-3417/11/16/7564

Similar Items