ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Implementation and evaluation of fast on-the-fly WFST composition algorithms

Tasuku Oonishi, Paul R. Dixon, Koji Iwano, Sadaoki Furui

When using Weighted Finite State Transducers (WFSTs) in speech recognition, on-the-fly composition approaches have been proposed as a method of reducing memory consumption and increasing flexibility during decoding. We have recently implemented several fast on-the-fly techniques, namely avoiding dead-end states, dynamic pushing and state sharing in our decoding engine. The goal of this paper is to provide a unified study of how the different on-the-fly techniques and online composition combinations effect speech recognition performance. The evaluations were performed on a large spontaneous speech recognition task and the results show that when using on-the-fly composition with a fully dynamically composed language model component the performance degrades substantially even when avoiding dead-end states. We then show in these cases the recognition performance can be dramatically improved with the addition of dynamic pushing and state sharing.

doi: 10.21437/Interspeech.2008-547

Cite as: Oonishi, T., Dixon, P.R., Iwano, K., Furui, S. (2008) Implementation and evaluation of fast on-the-fly WFST composition algorithms. Proc. Interspeech 2008, 2110-2113, doi: 10.21437/Interspeech.2008-547

  author={Tasuku Oonishi and Paul R. Dixon and Koji Iwano and Sadaoki Furui},
  title={{Implementation and evaluation of fast on-the-fly WFST composition algorithms}},
  booktitle={Proc. Interspeech 2008},