A binaural sound localization system using deep convolutional neural networks

Ying Xu, Saeed Afshar, Ram Kuber Singh, Runchun Wang, Andre van Schaik, Tara Julia Hamilton

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

11 Citations (Scopus)

Abstract

We propose a biologically inspired binaural sound localization system using a deep convolutional neural network (CNN) for reverberant environments. It utilizes a binaural Cascade of Asymmetric Resonators with Fast-Acting Compression (CAR-FAC) cochlear system to analyze binaural signals, a lateral inhibition function to sharpen temporal information of cochlear channels, and instantaneous correlation function on the two cochlear channels to encode binaural cues. The generated 2-D instantaneous correlation matrix (correlogram) encodes both interaural phase difference (IPD) cues and spectral information in a unified framework. Additionally, a sound onset detector is exploited to generate the correlograms only during sound onsets to remove interference from echoes. The onset correlograms are analyzed using a deep CNN for regression to the azimuthal angle of the sound. The proposed system was evaluated using experimental data in a reverberant environment, and displayed a root mean square localization error (RMSE) of 3.68° in the −90° to 90° range.
Original languageEnglish
Title of host publicationProceedings of the 2019 IEEE International Symposium on Circuits and Systems (ISCAS 2019), 26-29 May 2019, Sapporo, Japan
PublisherIEEE
Number of pages5
ISBN (Print)9781728103976
DOIs
Publication statusPublished - 2019
EventIEEE International Symposium on Circuits and Systems -
Duration: 26 May 2019 → …

Publication series

Name
ISSN (Print)0271-4310

Conference

ConferenceIEEE International Symposium on Circuits and Systems
Period26/05/19 → …

Keywords

  • cochlea
  • directional hearing
  • neural networks (computer science)
  • neuromorphics
  • reverberation
  • sound

Fingerprint

Dive into the research topics of 'A binaural sound localization system using deep convolutional neural networks'. Together they form a unique fingerprint.

Cite this