• myGriffith
    • Staff portal
    • Contact Us⌄
      • Future student enquiries 1800 677 728
      • Current student enquiries 1800 154 055
      • International enquiries +61 7 3735 6425
      • General enquiries 07 3735 7111
      • Online enquiries
      • Staff phonebook
    View Item 
    •   Home
    • Griffith Research Online
    • Conference outputs
    • View Item
    • Home
    • Griffith Research Online
    • Conference outputs
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

  • All of Griffith Research Online
    • Communities & Collections
    • Authors
    • By Issue Date
    • Titles
  • This Collection
    • Authors
    • By Issue Date
    • Titles
  • Statistics

  • Most Popular Items
  • Statistics by Country
  • Most Popular Authors
  • Support

  • Contact us
  • FAQs
  • Admin login

  • Login
  • Deep residual-dense lattice network for speech enhancement

    View/Open
    Nikzad475685-Accepted.pdf (756.1Kb)
    File version
    Accepted Manuscript (AM)
    Author(s)
    Nikzad, M
    Nicolson, Aaron
    Gao, Yongsheng
    Zhou, Jun
    Paliwal, Kuldip K.
    Shang, Fanhua
    Griffith University Author(s)
    Paliwal, Kuldip K.
    Zhou, Jun
    Gao, Yongsheng
    Nicolson, Aaron M.
    Nikzad Dehaji, Nick
    Year published
    2020
    Metadata
    Show full item record
    Abstract
    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 ...
    View more >
    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.
    View less >
    Conference Title
    Proceedings of the AAAI Conference on Artificial Intelligence
    Volume
    34
    Issue
    5
    DOI
    https://doi.org/10.1609/aaai.v34i05.6377
    Copyright Statement
    © 2020 AAAI Press. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. Please refer to the conference's website for access to the definitive, published version.
    Subject
    Electrical engineering
    Electronics, sensors and digital hardware
    Publication URI
    http://hdl.handle.net/10072/404394
    Collection
    • Conference outputs

    Footer

    Disclaimer

    • Privacy policy
    • Copyright matters
    • CRICOS Provider - 00233E

    Tagline

    • Gold Coast
    • Logan
    • Brisbane - Queensland, Australia
    First Peoples of Australia
    • Aboriginal
    • Torres Strait Islander