| 基于环境判别学习的高噪声命令语音识别系统 |
| |
| 引用本文： | 吕成国,韩纪庆,王承发,张磊. 基于环境判别学习的高噪声命令语音识别系统[J]. 哈尔滨工业大学学报, 2003, 35(2): 134-137 |
| |
| 作者姓名： | 吕成国 韩纪庆 王承发 张磊 |
| |
| 作者单位： | 哈尔滨工业大学,计算机科学与技术学院,黑龙江,哈尔滨,150001 |
| |
| 基金项目： | 国家自然科学基金资助项目 (60 0 85 0 0 1)，教育部留学人员科研启动基金资助项目 |
| |
| 摘 要： | 介绍了一种环境特征判别学习的Robust语音识别方法，该方法基于最小分类错误准则利用梯度下降法迭代地学习环境特征，实现了高噪声背景下命令语音识别系统。在不同级别背景噪声下，分别进行了有关信噪比、基本精度、抗噪能力以及系统对环境改变的适应性等实验。实验结果表明，系统在较高噪声背景下，有很好的识别效果，基本可满足应用领域的需要。
|
| 关 键 词： | 语音识别 环境特征 梯度下降法 噪声背景 语音信号处理 |
| 文章编号： | 0367-6234(2003)02-0134-04 |
| 修稿时间： | 2000-01-10 |
A speech recognition system in high noise background based on discriminative learning of environmental features |
| |
| LU Cheng guo,HAN Ji qing,WANG Cheng fa,ZHAN Lei. A speech recognition system in high noise background based on discriminative learning of environmental features[J]. Journal of Harbin Institute of Technology, 2003, 35(2): 134-137 |
| |
| Authors: | LU Cheng guo HAN Ji qing WANG Cheng fa ZHAN Lei |
| |
| Abstract: | A robust speech recognition system based on discriminative learning of environmental features is proposed for recognition of environmental features in high noise background, and a gradient descent algorithm was adopted for parameters optimization. Experiments were carried out at different levels of background noise for SNR,basic accuracy,noise-resistance and system environment adaptability. The experimental results show that the system has good recognition performance in high noisy environments. The system can meet different needs of application. |
| |
| Keywords: | speech recognition environmental features gradient descent algorithm noisy environment |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
