ISCA Archive Eurospeech 2001
ISCA Archive Eurospeech 2001

Transducer optimizations for tight-coupled decoding

Alexander Seward

In this paper we apply a framework of finite-state transducers (FST) to uniformly represent various information sources and data-structures used in speech recognition. These source models include context-free language models, phonology models, acoustic model information (Hidden Markov Models), and pronunciation dictionaries. We will describe how this unified representation can serve as a single input model for the recognizer. We will demonstrate how the application of various levels of optimizations can lead to a more compact representation of these transducers and evaluate the effects on recognition performance, in terms of accuracy and computational complexity.

doi: 10.21437/Eurospeech.2001-391

Cite as: Seward, A. (2001) Transducer optimizations for tight-coupled decoding. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1607-1612, doi: 10.21437/Eurospeech.2001-391

  author={Alexander Seward},
  title={{Transducer optimizations for tight-coupled decoding}},
  booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},