ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Utterance verification using modified segmental probability model

Bin Jia, Xiaoyan Zhu, Yupin Luo, Dongcheng Hu

Today speech recognition is requested not only to decode utterances into transcriptions, but also to determine the reliabilities of the result, by Utte-rance Verification (UV). With the conventional HMM, the measure of reliabilities can not be determined directly by the likelihoods of models. Whereas, Modified Segmental Probability Model (MSPM), suggested in this paper, with its norma-lized likelihood, facilitates rendering UV and speech recognition at the same time and as a whole. In the paper, Integrated Anti-word Model (IAM) is suggested, which is used to advance the measure of UV likelihood of MSPM. Some experiments show high perfor-mance and moderate computa-tion with IAM.


doi: 10.21437/Eurospeech.1999-15

Cite as: Jia, B., Zhu, X., Luo, Y., Hu, D. (1999) Utterance verification using modified segmental probability model. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 45-48, doi: 10.21437/Eurospeech.1999-15

@inproceedings{jia99_eurospeech,
  author={Bin Jia and Xiaoyan Zhu and Yupin Luo and Dongcheng Hu},
  title={{Utterance verification using modified segmental probability model}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={45--48},
  doi={10.21437/Eurospeech.1999-15}
}