Parallel training of neural networks for speech recognition

  • Authors:

  • Karel Veselý;Lukáý Burget;Frantiýek Grézl

  • Affiliations:

  • Speech@FIT, Brno University of Technology, Brno, Czech Republic;Speech@FIT, Brno University of Technology, Brno, Czech Republic;Speech@FIT, Brno University of Technology, Brno, Czech Republic

  • Venue:
  • TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The feed-forward multi-layer neural networks have significant importance in speech recognition. A new parallel-training tool TNet was designed and optimized for multiprocessor computers. The training acceleration rates are reported on a phoneme-state classification task.