| 自适应函数链神经网络在非特定人语音识别中的应用 |
| |
| 引用本文： | 赵新民,王玲.自适应函数链神经网络在非特定人语音识别中的应用[J].邵阳学院学报(自然科学版),2006,3(2):43-45. |
| |
| 作者姓名： | 赵新民 王玲 |
| |
| 作者单位： | 湖南师范大学,物理与信息科学学院,湖南,长沙,410081 |
| |
| 摘 要： | 根据加权倒谱距离测度，构造了一种用于非特定人语音识别的函数链神经网络，并结合所提出的自适应函数链神经网络学习算法，不但大大缩短了网络的学习时间，而且使得该网络具有较高的识别率，采用10人（5男、5女）的语音数据对汉语10个数字进行了实验，正确识别率为94．2％．
|
| 关 键 词： | 语音识别 自适应 神经网络 非特定人 |
| 文章编号： | 1672-7010（2006）02-0043-03 |
| 收稿时间： | 2006-03-06 |
| 修稿时间： | 2006年3月6日 |
Application on self-adaptive functional-link neural network in speaker-independent speech recognition |
| |
| ZHAO Xin-min,WANG Ling.Application on self-adaptive functional-link neural network in speaker-independent speech recognition[J].Journal of Shaoyang University:Science and Technology,2006,3(2):43-45. |
| |
| Authors: | ZHAO Xin-min WANG Ling |
| |
| Abstract: | The functional - link neural network for speaker- independent speech recognition is put forward based on weighted cepstral distance measure and self - adaptive functional - link neural network algorithm. The network has not only higher recognition rate but also shortening the training time. An experimental result using 10 numbers, which have been pronounced by 5 males and 5 females, shows that an average recognition rate of 94.2 %. |
| |
| Keywords: | Speech recognition self- adaptive neural network speaker - independent |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
