ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Exploiting the ASR n-best by tracking multiple dialog state hypotheses

Jason D. Williams

When the top ASR hypothesis is incorrect, often the correct hypothesis is listed as an alternative in the ASR N-Best list. Whereas traditional spoken dialog systems have struggled to exploit this information, this paper argues that a dialog model that tracks a distribution over multiple dialog states can improve dialog accuracy by making use of the entire N-Best list. The key element of the approach is a generative model of the N-Best list given the user's true hidden action. An evaluation on real dialog data verifies that dialog accuracy rates are improved by making use of the entire N-Best list.


doi: 10.21437/Interspeech.2008-61

Cite as: Williams, J.D. (2008) Exploiting the ASR n-best by tracking multiple dialog state hypotheses. Proc. Interspeech 2008, 191-194, doi: 10.21437/Interspeech.2008-61

@inproceedings{williams08_interspeech,
  author={Jason D. Williams},
  title={{Exploiting the ASR n-best by tracking multiple dialog state hypotheses}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={191--194},
  doi={10.21437/Interspeech.2008-61}
}