ISCA Archive ISCSLP 2002
ISCA Archive ISCSLP 2002

Confidence measures for large vocabulary continuous speech recognition

Ping Lv, Zuo-Ying Wang, Da-Jin Lu

Estimation confidence of the output hypothesis of a speech recognizer can be used in many practical applications of speech recognition technology. In this paper, we propose to estimate the confidence of a hypothesized word directly as its posterior probability. There are tow methods to calculate posterior probabilities, one of which is based on word graphs and the other is based on N-best lists. We present experiment results on database provided by China National 863. And we also use confidence measures in unsupervised speaker adaptation.


Cite as: Lv, P., Wang, Z.-Y., Lu, D.-J. (2002) Confidence measures for large vocabulary continuous speech recognition. Proc. International Symposium on Chinese Spoken Language Processing, paper 87

@inproceedings{lv02_iscslp,
  author={Ping Lv and Zuo-Ying Wang and Da-Jin Lu},
  title={{Confidence measures for large vocabulary continuous speech recognition}},
  year=2002,
  booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
  pages={paper 87}
}