| Objective evaluation of pronunciation of standard Chinese final based on formant pattern |
| |
| 引用本文： | References：. Objective evaluation of pronunciation of standard Chinese final based on formant pattern[J]. 声学学报：英文版, 2007, 26(2): 168-179 |
| |
| 作者姓名： | References： |
| |
| 作者单位： | Zhongke Xinli Speech Laboratory, Institute of Acoustics, The Chinese Academy of Sciences Beijing 100080 |
| |
| 摘 要： | A method used for objective evaluation of pronunciation of finals in standard Chinese is presented. The formant pattern of final is selected as the mam feature and an improved evaluation algorithm based on Support Vector Machine is proposed. In this algorithm, two-level classification strategy is employed. A full-classification model and a sub-classification model are trained for each final. The pronunciation quality is evaluated based on the classification results of this two-level strategy with scoring model of each final. The new evaluation method is compared with traditional methods such as Hidden Markov Model (HMM) posterior probability scoring method and feature of Mel-Frequency Cepstrum Coefficients (MFCC), and the results show that the performance is effectively improved by the proposed method. The correlation of scores between human testers and machine has achieved 82%.
|
| 关 键 词： | 共振峰类型 普通话 韵母 发音 读法 客观评价 |
| 修稿时间： | 2006-04-122006-09-15 |
Objective evaluation of pronunciation of standard Chinese final based on formant pattern |
| |
| DONG Bin,ZHAO Qingwei,YAN Yonghong. Objective evaluation of pronunciation of standard Chinese final based on formant pattern[J]. Chinese Journal of Acoustics, 2007, 26(2): 168-179 |
| |
| Authors: | DONG Bin ZHAO Qingwei YAN Yonghong |
| |
| Abstract: | A method used for objective evaluation of pronunciation of finals in standard Chinese is presented. The formant pattern of final is selected as the main feature and an improved evaluation algorithm based on Support Vector Machine is proposed. In this algorithm, two-level classification strategy is employed. A full-classification model and a sub-classification model are trained for each final. The pronunciation quality is evaluated based on the classification results of this two-level strategy with scoring model of each final. The new evaluation method is compared with traditional methods such as Hidden Markov Model (HMM) posterior probability scoring method and feature of Mel-Frequency Cepstrum Coefficients (MFCC), and the results show that the performance is effectively improved by the proposed method. The correlation of scores between human testers and machine has achieved 82%. |
| |
| Keywords: | |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
