@inproceedings{f11d43e5632d49b295ec217fc29af539,
title = "An SVM-based Mandarin pronunciation quality assessment system",
abstract = "This paper presents our Mandarin pronunciation quality assessment system for the examination of Putonghua Shuiping Kaoshi (PSK) and investigates a novel Support Vector Machine (SVM) based method to improve its assessment accuracy. Firstly, an selective speaker adaptation module is introduced, in which we select well pronounced speech from results of the first-pass automatic pronunciation scoring as the adaptation data, and adopt Maximum Likelihood Linear Regression to update the acoustic model (AM). Then, compared with the traditional triphone based AM, the monophone based AM is studied. Finally, we propose a new method of incorporating all kinds of posterior probabilities using SVM classifier. Experimental results show that the average correlation coefficient between machine and human scores is improved from 83.72% to 85.48%. It suggests that the two methods of selective speaker adaptation and multi-model combination using SVM are very effective to improve the accuracy of pronunciation quality assessment.",
keywords = "CALL, Pronunciation Quality Assessment, Speaker Adaptation, Speech Recognition, SVM",
author = "Fengpei Ge and Fuping Pan and Changliang Liu and Bin Dong and Chan, {Shui duen} and Xinhua Zhu and Yonghong Yan",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2009.; 6th International Symposium of Neural Networks, ISNN 2009 ; Conference date: 26-05-2009 Through 29-05-2009",
year = "2009",
doi = "10.1007/978-3-642-01216-7_27",
language = "English",
series = "Advances in Intelligent and Soft Computing",
publisher = "Springer Verlag",
pages = "255--265",
editor = "Hongwei Wang and Yi Shen and Zhigang Zeng and Tingwen Huang",
booktitle = "Advances in Intelligent and Soft Computing",
address = "Germany",
}