DCTNet and PCANet for acoustic signal feature extraction

Yin Xian, Andrew Thompson, Xiaobai Sun, Douglas Nowacek, Loren Nolte

Research output: Working paperPreprint

Abstract

We introduce the use of DCTNet, an efficient approximation and alternative to PCANet, for acoustic signal classification. In PCANet, the eigenfunctions of the local sample covariance matrix (PCA) are used as filterbanks for convolution and feature extraction. When the eigenfunctions are well approximated by the Discrete Cosine Transform (DCT) functions, each layer of of PCANet and DCTNet is essentially a time-frequency representation. We relate DCTNet to spectral feature representation methods, such as the the short time Fourier transform (STFT), spectrogram and linear frequency spectral coefficients (LFSC). Experimental results on whale vocalization data show that DCTNet improves classification rate, demonstrating DCTNet's applicability to signal processing problems such as underwater acoustics.
Original languageEnglish
PublisherarXiv
Number of pages6
DOIs
Publication statusPublished - 28 Apr 2016

Publication series

NamearXiv

User-Defined Keywords

  • Convolutional networ
  • PCA
  • DCT
  • filterbanks
  • acoustic perception
  • spectral clustering
  • whale vocalizations

Fingerprint

Dive into the research topics of 'DCTNet and PCANet for acoustic signal feature extraction'. Together they form a unique fingerprint.

Cite this