识别正确率和抗噪性能是语音识别的研究重点，而识别响应速度也是决定系统实用化的关键 文章改进了传统的动态时间弯折算

法结构，将其应用于实时说话人辨识系统中，极大地提高了系统运行速度，随着待识别语音数目的增多，该算法优势更加明显 实验表明，

在不影响系统识别率的情况下，该方法使系统的运行速度平均提高了1.5 倍-Identify the correct rate and the anti-noise performance is the focus of speech recognition research, but also decided to identify the response speed of system utilities to improve the key article of the traditional structure of Dynamic Time Warping algorithm will be applied to real-time speaker identification system, greatly increase the speed of the system, with the question of an increase in the number of voice recognition, the algorithm is more obvious advantages of the experiment showed that the recognition rate does not affect the system' s case, the method of operation of the system increased the speed of an average of 1.5 times