| 基于变帧率训练的HMM汉语人名识别 |
| |
| 引用本文： | 刘刚,张洪刚,郭军. 基于变帧率训练的HMM汉语人名识别[J]. 中文信息学报, 2001, 15(1): 40-45 |
| |
| 作者姓名： | 刘刚 张洪刚 郭军 |
| |
| 作者单位： | 北京邮电大学信息工程系 |
| |
| 基金项目： | 高等学校骨干教师资助! ( 2 0 0 0 -65) |
| |
| 摘 要： | 本文针对语音识别中HMM模型需要大量训练,而在某些实际应用中不可能训练多次的问题,提出一种基于余弦整形变换的变帧率训练方法,并在人名声控拨号系统中进行实验,在训练一次的条件下,系统识别率提高4.2%。实验表明,该方法对解决语音识别系统中训练数据少的问题具有明显效果。
|
| 关 键 词： | 语音识别 HMM 余弦整形变换 变帧率 |
| 修稿时间： | 2000-03-09 |
Mandarin Name Recognition Based on Variable Frame Rate HMM Training |
| |
| LIU Gang,ZHANG Hong-gang,GUO Jun. Mandarin Name Recognition Based on Variable Frame Rate HMM Training[J]. Journal of Chinese Information Processing, 2001, 15(1): 40-45 |
| |
| Authors: | LIU Gang ZHANG Hong-gang GUO Jun |
| |
| Affiliation: | Dept.of Information Engineering of Beijing University of Post and Telecomm |
| |
| Abstract: | In speech recognition HMM requires a large number of data for training,however,in some applications it is impractical.Therefore,a VFR training method based on pattern transform method with consine function is presented,in this paper,to solve this problem.We apply this original method to a voice control dialling system.System accuracy increases 4.2% on the condition of training just only one time.It isdemonstrated that this method has obvious effect on the scarcity of training data. |
| |
| Keywords: | speech recognition HMM pattern transform method with cosine function variable frame rate |
| 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 |
