Efficient Context Aggregation for End-to-End Speech Enhancement Using a Densely Connected Convolutional and Recurrent Network

08/18/2019
by   Kai Zhen, et al.
0

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a high-resolution time domain signal with an affordable model complexity still remains challenging. In this paper, we propose a hybrid architecture, incorporating densely connected convolutional networks (DenseNet) and gated recurrent units (GRU), to enable dual-level temporal context aggregation. Due to the dense connectivity pattern and a cross-component identical shortcut, the proposed model consistently outperforms competing convolutional baselines with an average STOI improvement of 0.23 and PESQ of 1.38 at three SNR levels. In addition, the proposed hybrid architecture is computationally efficient with 1.38 million parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/18/2019

A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement

In speech enhancement, an end-to-end deep neural network converts a nois...
research
02/02/2020

Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks

In recent decades, neural network based methods have significantly impro...
research
10/28/2022

Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Most neural network speech enhancement models ignore speech production m...
research
10/02/2021

End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression

Echo and noise suppression is an integral part of a full-duplex communic...
research
11/25/2019

Invertible DNN-based nonlinear time-frequency transform for speech enhancement

We propose an end-to-end speech enhancement method with trainable time-f...
research
11/16/2018

Using recurrences in time and frequency within U-net architecture for speech enhancement

When designing fully-convolutional neural network, there is a trade-off ...
research
03/22/2020

Monaural Speech Enhancement with Recursive Learning in the Time Domain

In this paper, we propose a type of neural network with recursive learni...

Please sign up or login with your details

Forgot password? Click here to reset