Journal of Applied Mathematics
Volume 2012 (2012), Article ID 548341, 8 pages
Research Article

Optimization of Spoken Term Detection System

1Institute of Informatics, Qingdao University of Science and Technology, Qingdao 266061, China
2Thinkit Speech Laboratory, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China

Received 31 December 2011; Accepted 24 January 2012

Academic Editor: Baocang Ding

Copyright © 2012 Chuanxu Wang and Pengyuan Zhang. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Generally speaking, spoken term detection system will degrade significantly because of mismatch between acoustic model and spontaneous speech. This paper presents an improved spoken term detection strategy, which integrated with a novel phoneme confusion matrix and an improved word-level minimum classification error (MCE) training method. The first technique is presented to improve spoken term detection rate while the second one is adopted to reject false accepts. On mandarin conversational telephone speech (CTS), the proposed methods reduce the equal error rate (EER) by 8.4% in relative.