Parallel Structure in an Integrated Speech-Recognition Network

  • Authors:
  • Martin Fleury;Andy C. Downton;Adrian F. Clark

  • Affiliations:
  • -;-;-

  • Venue:
  • Euro-Par '99 Proceedings of the 5th International Euro-Par Conference on Parallel Processing
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

Large-vocabulary continuous-speech recognition (LVCR) speaker-independent systems which integrate cross-word context dependent acoustic models and n-gram language models are difficult to parallelize because of their interwoven structure, large dynamic data structures, and complex object-oriented software design. This paper shows how retrospective decomposition can be achieved if a quantitative analysis is made of dynamic system behaviour. A design which accommodates unforeseen effects and future modifications is presented.