| 基于改进的DTW算法的仿真与分析 |
| |
| 引用本文： | 崔光照,吴晓平,路康.基于改进的DTW算法的仿真与分析[J].福建工程学院学报,2004,2(2):149-151,175. |
| |
| 作者姓名： | 崔光照 吴晓平 路康 |
| |
| 作者单位： | 郑州轻工业学院信息与控制工程系,河南,郑州,450002 |
| |
| 摘 要： | 传统的DTW算法着重于时间规整和间距测量的概念，对数据的可靠性没有进行有效的分析，且对连续词的识别效果不明显。基于松弛起始点和分段思想的改进DTW算法，可以改善明阿算法的缺陷。通过对语音样本0．9在MATLAB6．5上的仿真实现与分析表明，采用改进后的DTW算法具有良好的语音识别效果。
|
| 关 键 词： | 语音识别 端点检测 线性预测 |
| 文章编号： | 1672-4348(2004)02-0149-03 |
| 修稿时间： | 2004年3月7日 |
The simulation and analysis based on improved DTW algorithm |
| |
| CUI Guang-zhao,WU Xiao-ping,LU Kang.The simulation and analysis based on improved DTW algorithm[J].Journal of Fujian University of Technology,2004,2(2):149-151,175. |
| |
| Authors: | CUI Guang-zhao WU Xiao-ping LU Kang |
| |
| Abstract: | The traditional DTW algorithm is mainly concerned with the concept of time-coordinate and space-measurement, but it can not provide effective analysis of data-reliability and distinct recognition for continuous words. An improved DTW algorithm that can overcome the limitations is presented based on the flabby initiative point and the subsection idea. Analysis of the simulation results from speech samples of zero to nine on the MATLAB6.5 shows that the improved DTW algorithm can provide better recognition of speech sounds. |
| |
| Keywords: | speech recognition point examination linear prediction |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
