Close
Metadata

%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2015/07.31.20.05
%2 sid.inpe.br/sibgrapi/2015/07.31.20.05.18
%T Design of reservoir computing systems for noise-robust speech and handwriting recognition
%D 2015
%A Jalalvand, Azarakhsh,
%A Demuynck, Kris,
%A De Neve, Wesley,
%A Van de Walle, Rik,
%A Martens, Jean-Pierre,
%@affiliation Ghent University - iMinds
%@affiliation Ghent University - iMinds
%@affiliation Ghent University - iMinds
%@affiliation Ghent University - iMinds
%@affiliation Ghent University - iMinds
%E Segundo, Maurício Pamplona,
%E Faria, Fabio Augusto,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador
%8 Aug. 26-29, 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K reservoir computing networks, speech processing, image processing, artificial neural networks, noise robustness.
%X In this work, we address the noise robustness of the pattern recognition systems by investigating the application of Reservoir Computing Networks (RCNs) on speech and image recognition tasks. Our work introduces different architectures of RCN-based systems along with a coherent task-independent strategy to optimize the reservoir parameters. We show that such systems are more robust that the state-of-the-arts in the presence of noise and RCNs can be used for both robust recognition tasks as well as denoising approaches. Moreover, the successful application of RCNs on different tasks using the proposed strategy supports our claim that it is task-independent.
%@language en
%3 Aza_SIBGRAPI2015.pdf


Close