| 一种基于高维空间覆盖动态搜索方法的 非特定人连续数字语音识别的研究 |
| |
| 引用本文： | 王守觉,潘晓霞,徐春燕,陈旭,安冬,曹文明.一种基于高维空间覆盖动态搜索方法的 非特定人连续数字语音识别的研究[J].电子学报,2005,33(10):1790-1793. |
| |
| 作者姓名： | 王守觉 潘晓霞 徐春燕 陈旭 安冬 曹文明 |
| |
| 作者单位： | 1. 中国科学院半导体研究所,北京 100083;2. 浙江工业大学智能信息系统研究所,浙江杭州 310014 |
| |
| 摘 要： | 本文使用高维空间点分布分析原理,在仿生模式识别高维空间点覆盖原理的基础上,提出了一种基于高维空间点覆盖动态搜索理论的非特定人连续数字语音识别的新算法,这种算法可以不经过端点检测和分割,通过对被识别连续数字语音直接进行动态搜索,得到被识别语音到各类高维空间覆盖范围的距离随时间变化曲线,通过距离曲线上的极小值点进行识别.
|
| 关 键 词： | 连续语音识别 高维空间点覆盖 非特定人语音识别 |
| 文章编号： | 0372-2112（2005）10-1790-04 |
| 收稿时间： | 2004-07-05 |
| 修稿时间： | 2004-07-052005-07-21 |
Research on Speaker-Independent Continuous Figure Speech-Recognition Based on High-Dimensional Space Covering and Dynamic Scanning |
| |
| WANG Shou-jue,PAN Xiao-xia,XU Chun-yan,CHEN Xu,AN Dong,CAO Wen-ming.Research on Speaker-Independent Continuous Figure Speech-Recognition Based on High-Dimensional Space Covering and Dynamic Scanning[J].Acta Electronica Sinica,2005,33(10):1790-1793. |
| |
| Authors: | WANG Shou-jue PAN Xiao-xia XU Chun-yan CHEN Xu AN Dong CAO Wen-ming |
| |
| Affiliation: | 1. Lab of Artificial Neural Networks,Institute of Semiconductors,CAS,Beijing 100083,China;2. Research Institute of Intelligent Information System,Zhejiang University of Technology,Hangzhou,Zhejiang 310014,China |
| |
| Abstract: | Through analyzing samples distribution in high dimensional space,a novel algorithm for speaker-independent continuous figure speech recognition is presented based on high-dimensional space covering,biomimetic pattern recognition and dynamic scanning in this paper.Without endpoints detection and segmenting the continuous speech is dynamic scanned,then distance curves from the continuous speech to every kind of covering area in high dimensional space are obtained.The continuous speech is recognized by detecting the minimum values in the curves. |
| |
| Keywords: | continuous speech recognition high-dimensional space covering speaker independent |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子学报》浏览原始摘要信息 |
|
点击此处可从《电子学报》下载全文 |
|
