DeepAI AI Chat
Log In Sign Up

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

by   Kai Zhen, et al.
Indiana University Bloomington

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.


page 1

page 2

page 3

page 4


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...

Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks

In recent decades, neural network based methods have significantly impro...

RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement

Most current speech enhancement models use spectrogram features that req...

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

When designing fully-convolutional neural network, there is a trade-off ...

HGCN: harmonic gated compensation network for speech enhancement

Mask processing in the time-frequency (T-F) domain through the neural ne...

Sparse Mixture of Local Experts for Efficient Speech Enhancement

In this paper, we investigate a deep learning approach for speech denois...