基于环境判别学习的高噪声命令语音识别系统  

A speech recognition system in high noise background based on discriminative learning of environmental features

作　　者：吕成国[1] 韩纪庆[1] 王承发[1] 张磊[1] 

机构地区：[1]哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨150001

出　　处：《哈尔滨工业大学学报》2003年第2期134-137,共4页Journal of Harbin Institute of Technology

基　　金：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 。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.

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 

分 类 号：TN912.34[电子电信—通信与信息系统]