ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Novel two-pass search strategy using time-asynchronous shortest-first second-pass beam search

Atsunori Ogawa, Yoshiaki Noda, Shoichi Matsunaga

In this paper, we describe a novel two-pass search strategy for large vocabulary continuous speech recognition. The first-pass of this strategy uses a regular time-synchronous beam search with rough models to generate a word lattice. Then, the second-pass search derives exact results from the word lattice using more accurate models. This search is “time-asynchronous shortest- first beam search”, which has two novel features: a time-asynchronous beam search mechanism using heuristics that are scores on the word lattice nodes and a strict pruning scheme using shortest-first hypothesis extension. 20k-word Japanese broadcast news recognition experiments show that our second-pass search is more accurate and more efficient than either N-best rescoring or A* search that are conventional second-pass search methods.


Cite as: Ogawa, A., Noda, Y., Matsunaga, S. (2000) Novel two-pass search strategy using time-asynchronous shortest-first second-pass beam search. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 290-293

@inproceedings{ogawa00_icslp,
  author={Atsunori Ogawa and Yoshiaki Noda and Shoichi Matsunaga},
  title={{Novel two-pass search strategy using time-asynchronous shortest-first second-pass beam search}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 4, 290-293}
}