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

Saved in:
Bibliographic Details
Published in:Applied sciences 2022-04, Vol.12 (7), p.3461
Main Authors: Song, Zhendong, Ma, Yupeng, Tan, Fang, Feng, Xiaoyi
Format: Article
Language:English
Subjects:
Algorithms
Convolution
Deep learning
Encoders-Decoders
hybrid dilated convolution
Information processing
Methods
Neural networks
Noise
Receptive field
recurrent convolution
Speech
speech enhancement
Speech processing
time domain
Voice recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 features of a noisy input frame. In the HDM, the dilated convolution is used to expand the receptive field of the network model. In contrast, the standard convolution is used to make up for the under-utilized local information of the dilated convolution. The decoder is used to reconstruct enhanced frames. The recursive recurrent convolutional network uses GRU to solve the problem of multiple training parameters and complex structures. State-of-the-art results are achieved on two commonly used speech datasets.
ISSN:2076-3417
2076-3417
DOI:10.3390/app12073461