Deep Residual-Dense Lattice Network for Speech Enhancement

02/27/2020
by   Mohammad Nikzad, et al.
0

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during training, feature diminution of shallow layer outputs can occur due to repetitive summations with deeper layer outputs. One strategy to improve feature re-usage is to fuse both ResNets and densely connected CNNs (DenseNets). DenseNets, however, over-allocate parameters for feature re-usage. Motivated by this, we propose the residual-dense lattice network (RDL-Net), which is a new CNN for speech enhancement that employs both residual and dense aggregations without over-allocating parameters for feature re-usage. This is managed through the topology of the RDL blocks, which limit the number of outputs used for dense aggregations. Our extensive experimental investigation shows that RDL-Nets are able to achieve a higher speech enhancement performance than CNNs that employ residual and/or dense aggregations. RDL-Nets also use substantially fewer parameters and have a lower computational requirement. Furthermore, we demonstrate that RDL-Nets outperform many state-of-the-art deep learning approaches to speech enhancement.

READ FULL TEXT
research
09/03/2020

Dense CNN with Self-Attention for Time-Domain Speech Enhancement

Speech enhancement in the time domain is becoming increasingly popular i...
research
06/20/2019

A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting

Robustness against noise is critical for keyword spotting (KWS) in real-...
research
11/10/2022

Speech Enhancement with Fullband-Subband Cross-Attention Network

FullSubNet has shown its promising performance on speech enhancement by ...
research
11/17/2021

BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement

In this paper, we present a blockwise optimization method for masking-ba...
research
01/13/2022

Learning Enhancement of CNNs via Separation Index Maximizing at the First Convolutional Layer

In this paper, a straightforward enhancement learning algorithm based on...
research
01/30/2020

Channel-Attention Dense U-Net for Multichannel Speech Enhancement

Supervised deep learning has gained significant attention for speech enh...
research
04/09/2019

Speech Enhancement with Wide Residual Networks in Reverberant Environments

This paper proposes a speech enhancement method which exploits the high ...

Please sign up or login with your details

Forgot password? Click here to reset