ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Speed improvement of the tree-based time asynchronous search

Miroslav Novak, Michael Picheny

The IBM large vocabulary continuous speech recog- nition system is based on an asynchronous stack de- coding scheme. This is essentially a tree search, as described in [1]. The main advantages - ecient mem- ory utilization and a single-pass search strategy - make the system extremely suitable for real-time applica- tions. This article describes further improvements in eciency of the search method. These improvements are achieved in part by more ecient word to con- text dependent acoustic model expansion, producing equivalent search results and thus not affecting the recognition accuracy. Additional improvements are achieved by introducing an approximation in the com- putation of the likelihood of the hypothesized path. The basic idea is to allow sharing of some branches in the search tree and results in effectively a tree to network transformation.

Rabiner, L.R., Juang, B.H., \An introduction to hidden Markov Models", IEEE ASSP Mag., Vol. 3, pp. 4-16, Jan. 1986


Cite as: Novak, M., Picheny, M. (2000) Speed improvement of the tree-based time asynchronous search. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 334-337

@inproceedings{novak00_icslp,
  author={Miroslav Novak and Michael Picheny},
  title={{Speed improvement of the tree-based time asynchronous search}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 4, 334-337}
}