ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Fast n-gram language model look-ahead for decoders with static pronunciation prefix trees

Marijn Huijbregts, Roeland Ordelman, Franciska de Jong

Decoders that make use of token-passing restrict their search space by various types of token pruning. With use of the Language Model Look-Ahead (LMLA) technique it is possible to increase the number of tokens that can be pruned without loss of decoding precision. Unfortunately, for token passing decoders that use single static pronunciation prefix trees, full n-gram LMLA increases the needed number of language model probability calculations considerably. In this paper a method for applying full n-gram LMLA in a decoder with a single static pronunciation tree is introduced. The experiments show that this method improves the speed of the decoder without an increase of search errors.


doi: 10.21437/Interspeech.2008-262

Cite as: Huijbregts, M., Ordelman, R., Jong, F.d. (2008) Fast n-gram language model look-ahead for decoders with static pronunciation prefix trees. Proc. Interspeech 2008, 1582-1585, doi: 10.21437/Interspeech.2008-262

@inproceedings{huijbregts08_interspeech,
  author={Marijn Huijbregts and Roeland Ordelman and Franciska de Jong},
  title={{Fast n-gram language model look-ahead for decoders with static pronunciation prefix trees}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={1582--1585},
  doi={10.21437/Interspeech.2008-262}
}