logo Idiap Research Institute        
 [BibTeX] [Marc21]
Deep Neural Networks for Multiple Speaker Detection and Localization
Type of publication: Conference paper
Citation: He_ICRA_2018
Publication status: Published
Booktitle: 2018 IEEE International Conference on Robotics and Automation (ICRA)
Year: 2018
Month: May
Pages: 74-79
Location: Brisbane, AUSTRALIA
ISSN: 1050-4729
ISBN: 978-1-5386-3081-5
Crossref: He_Idiap-RR-02-2018:
DOI: 10.1109/ICRA.2018.8461267
Abstract: We propose to use neural networks for simultaneous detection and localization of multiple sound sources in human-robot interaction. In contrast to conventional signal processing techniques, neural network-based sound source localization methods require fewer strong assumptions about the environment. Previous neural network-based methods have been focusing on localizing a single sound source, which do not extend to multiple sources in terms of detection and localization. In this paper, we thus propose a likelihood-based encoding of the network output, which naturally allows the detection of an arbitrary number of sources. In addition, we investigate the use of sub-band cross-correlation information as features for better localization in sound mixtures, as well as three different network architectures based on different motivations. Experiments on real data recorded from a robot show that our proposed methods significantly outperform the popular spatial spectrum-based approaches.
Keywords: acoustic generators, Artificial Neural Networks, deep neural networks, Delays, Encoding, Estimation, human-robot interaction, likelihood-based encoding, microphone arrays, Microphones, multiple sound sources, multiple speaker detection, network output, neural nets, neural network-based sound source localization methods, Robots, simultaneous detection, single sound source, sound mixtures, spatial spectrum-based approaches, speaker recognition
Projects Idiap
Authors He, Weipeng
Motlicek, Petr
Odobez, Jean-Marc
Added by: [UNK]
Total mark: 0
  • He_ICRA_2018.pdf