Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99) Budapest, Hungary September 5-9, 1999

Utterance Verification using Modified Segmental Probability Model

Bin Jia (1), Xiaoyan Zhu (2), Yupin Luo (1), Dongcheng Hu (1)

(1) Dept. of Automation, Tsinghua University, Beijing, China
(2) Dept. of Computer Science and Technology, Tsinghua University, Beijing, China

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.

Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Jia, Bin / Zhu, Xiaoyan / Luo, Yupin / Hu, Dongcheng (1999): "Utterance verification using modified segmental probability model", In EUROSPEECH'99, 45-48.