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

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.