孤立词语音识别算法研究与设计  

Research on and Implementation of Algorithm of Isolated Word Speech Recognition

作　　者：吴佳龙[1] 李坤[1] 刘中[1] 

机构地区：[1]西安电子科技大学电子工程学院,陕西西安710071

出　　处：《电子科技》2015年第2期22-25,29,共5页Electronic Science and Technology

摘　　要：语音识别在非接触式控制系统中的应用普遍,基于数字化平台的孤立词语音识别技术是一项重要的研究方向。文中介绍了短时能零差断点检测算法,采用MEL频率倒谱系数特征参数提取算法和动态时间规整的模型匹配方法,并用Matlab进行仿真,仿真结果表明,系统具有较强的实时性和较高的识别率。The technology of speech recognition has been widely used on non-contacting system,where one of the important research directions is the isolated-word speech recognition system based on the digital platform. Endpoint detection,MFCC feature parameters extraction and DTW pattern recognition for the voice signal have been implemented and simulated by Matlab. The results show that the system has strong instantaneity and high recognition rate.

关 键 词：孤立词 语音识别 MFCC DTW 

分 类 号：TN912.34[电子电信—通信与信息系统]