Deep Residual-Dense Lattice Network for Speech Enhancement

By Mohammad Nikzad, Aaron Nicolson, Yongsheng Gao, Jun Zhou, Kuldip K. Paliwal, Fanhua Shang. 2020

42 citations recorded by the source corpus.

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. Availability: https://github.com/nick-nikzad/RDL-SE.

Subfields: Electrical and Electronic Engineering, Human-Computer Interaction, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

  1. Gabriel Synnaeve

In Signal Processing

  1. Yossi Adi
  2. Gabriel Synnaeve
  3. Alexandre D'efossez
  4. Wei-Ning Hsu
  5. Ronan Collobert
  6. Jade Copet
  7. Jinyu Li
  8. Bowen Shi

Citations in the corpus