| 一种小词汇量快速语音识别系统的实现 |
| |
| 引用本文： | 刘建辉,卢珞先,黄涛. 一种小词汇量快速语音识别系统的实现[J]. 武汉理工大学学报(信息与管理工程版), 2006, 28(2): 10-13 |
| |
| 作者姓名： | 刘建辉 卢珞先 黄涛 |
| |
| 作者单位： | 武汉理工大学,智能信息系统研究所,湖北,武汉,430070 |
| |
| 摘 要： | 介绍了一种小词汇量的语音识别方法。在传统的DTW语音识别的基础上,通过放宽端点、对路径进行斜率限制和改进局部路径限制等方法,使系统能够实现快速的识别响应,尤其是对于小词汇量和特定人识别,可以有效地提高响应速度和识别率。
|
| 关 键 词： | 语音识别 线性预测 端点检测 |
| 文章编号： | 1007-144X（2006）02-0010-04 |
| 收稿时间： | 2005-08-07 |
| 修稿时间： | 2005-08-07 |
Implementation of Fast Speech Recognition System for Small Vocabulary |
| |
| Liu Jianhui,Lu Luoxian,Huang Tao. Implementation of Fast Speech Recognition System for Small Vocabulary[J]. Journal of Wuhan University of Technology(Information & Management Engineering), 2006, 28(2): 10-13 |
| |
| Authors: | Liu Jianhui Lu Luoxian Huang Tao |
| |
| Affiliation: | Institute of Intelligence and Information System, WUT, Wuhan 430070, China |
| |
| Abstract: | A fast speech recognition system for small vocabulary is presented.Based on traditional DTW speech recognition and through relaxing extreme,limiting route's slope and improving some routes,the system can recognize and respond quickly especially when applied in small vocabulary speech recognition and speaker-dependent recognition. |
| |
| Keywords: | DTW |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
