Hybrid Dilated and Recursive Recurrent Convolution Network for Time-Domain Speech Enhancement

Hybrid Dilated and Recursive Recurrent Convolution Network for Time-Domain Speech Enhancement

In this paper, we propose a fully convolutional neural network based on recursive recurrent convolution for monaural speech enhancement in the time domain. The proposed network is an encoder-decoder structure using a series of hybrid dilated modules (HDM). The encoder creates low-dimensional feature...

Full description

Bibliographic Details
Main Authors: Zhendong Song, Yupeng Ma, Fang Tan, Xiaoyi Feng
Format: Article
Language:English
Published: MDPI AG 2022-03-01
Series:Applied Sciences
Subjects:
speech enhancement
time domain
hybrid dilated convolution
recurrent convolution
Online Access:https://www.mdpi.com/2076-3417/12/7/3461

Internet

https://www.mdpi.com/2076-3417/12/7/3461

Similar Items