| 中文语音确认中子词置信度性能的研究 |
| |
| 引用本文： | 孙成立,刘刚,郭军. 中文语音确认中子词置信度性能的研究[J]. 中文信息学报, 2008, 22(2): 106-109,128 |
| |
| 作者姓名： | 孙成立 刘刚 郭军 |
| |
| 作者单位： | 1. 北京邮电大学 信息工程学院, 北京 100876; 2. 石家庄经济学院 信息工程学院, 河北 石家庄050031
|
| |
| 基金项目： | 国家863计划资助项目(2006AA010102)，河北省科技厅资助项目(052135147,042135105)，河北省教育厅资助项目(2005340) |
| |
| 摘 要： | 本文提出了一种基于最小分类错误准则(MCE)的子词权重参数估计算法,通过MCE训练得到子词的权重系数。子词对词级置信度贡献量的研究表明: 韵母的确认能力显著好于声母,在置信性能方面比声母更加稳定和可靠,区分能力优于声母。在130个关键词的关键词检测系统实验表明,采用不同子词贡献权重比等贡献权重时等错误率下降3.05%。
|
| 关 键 词： | 计算机应用 中文信息处理 语音确认 置信度 似然比检验 最小分类错误 |
| 文章编号： | 1003-0077（2008）02-0106-04 |
| 收稿时间： | 2007-05-30 |
| 修稿时间： | 2007-12-05 |
Investigation of Subwords Confidence Performance in Chinese Speech Verification |
| |
| SUN Cheng-li,LIU Gang,GUO Jun. Investigation of Subwords Confidence Performance in Chinese Speech Verification[J]. Journal of Chinese Information Processing, 2008, 22(2): 106-109,128 |
| |
| Authors: | SUN Cheng-li LIU Gang GUO Jun |
| |
| Affiliation: | 1.School of Information Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. School of Information Engineering, Shijiazhuang University of Economics, Shijiazhuang,Hebei 050031, China
|
| |
| Abstract: | A Minimum Classification Error(MCE) criterion based sub-words weighting parameters estimation algorithm is proposed in which the sub-word weighting parameters are derived by the MCE training.Investigation of the contribution of different sub-words on the word-level confidence measure show that Finals significantly outperform the Initials with more reliability and stability in confidence performance,and Finals have more discriminative power than those of Initials.Experiment on keyword spotting system with 130 keywords shows that the system with different sub-word weighting contribution achieved a relative Equal Error Rate(EER) reduction of 3.05% compared with the equal weighting contribution case. |
| |
| Keywords: | computer application Chinese information processing utterance verification confidence measure likelihood ratio test MCE |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《中文信息学报》浏览原始摘要信息 |
|
点击此处可从《中文信息学报》下载全文 |
