ISCA Archive IDS 2002
ISCA Archive IDS 2002

On the use of structures in language models for dialogue -specific solutions For specific problems

Yannick Estève, Christian Raymond, Renato De Mori

Availability of large corpora for training language models to develop dialogue systems is rare. Fortunately, for specific dialogue application, many sentences follow a limited number of typical patterns. In a language like French, frequent errors are due to homophones. Three paradigms are proposed in this paper to rescore a trellis of hypothesized words. They are based on sentence patterns detected in the most likely sentence hypothesized in a first recognition phase.


Cite as: Estève, Y., Raymond, C., De Mori, R. (2002) On the use of structures in language models for dialogue -specific solutions For specific problems. Proc. Multi-Modal Dialogue in Mobile Environments, paper 38

@inproceedings{esteve02_ids,
  author={Yannick Estève and Christian Raymond and Renato {De Mori}},
  title={{On the use of structures in language models for dialogue -specific solutions For specific problems}},
  year=2002,
  booktitle={Proc. Multi-Modal Dialogue in Mobile Environments},
  pages={paper 38}
}