机器人语音识别实验设计与实现

摘要

基于Matlab设计了以动态时间规整(dynamic time warping,DTW)算法和Mel频率倒谱系数(Melfrequency cepstrum coefficients,MFCC)参数提取算法为基础的孤立词自动语音识别系统；然后结合机器人语音识别的需求,基于凌阳SPCE061A设计了语音识别应用系统.结合上述两部分工作,设计、实现了机器人语音识别系统演示实验和机器人语音识别半开放实验,实现效果达到预期实验设计目标.%The isolated-words speech recognition system is implemented based on dynamic time warping algorithm and Mel frequency cepstrum coefficients parameters extraction in Matlab. And then robot speech recognition is implemented based on Lingyang SPCE061A considering application requirements of robot. Based on work above, demonstrating experiment and experiment with open algorithm of robot speech recognition are designed. Results show that experiments designed meet the design aims.