ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Transducer composition for context-dependent network expansion

Michael Riley, Fernando Pereira, Mehryar Mohri

Context-dependent models for language units are essential in high-accuracy speech recognition. However, standard speech recognition frameworks are based on the substitution of level models for higher-level units. Since substitution cannot express context-dependency constraints, actual recognizers use restrictive model-structure assumptions and specialized code for context-dependent models, leading to decreased flexibility and lost opportunities for automatic model optimization. Instead, we propose a recognition framework that builds in the possibility of context dependency from the start by using weighted finite-state transduction rather than substitution. The framework is mented with a general demand-driven transducer composition algorithm that allows great flexibility in model structure, form of context dependency and network expansion method, while achieving competitive recognition performance.

doi: 10.21437/Eurospeech.1997-415

Cite as: Riley, M., Pereira, F., Mohri, M. (1997) Transducer composition for context-dependent network expansion. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1427-1430, doi: 10.21437/Eurospeech.1997-415

  author={Michael Riley and Fernando Pereira and Mehryar Mohri},
  title={{Transducer composition for context-dependent network expansion}},
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},