文件名称:speech_recognition_based_on_DTW
介绍说明--下载内容均来自于网络,请自行研究使用
基于动态时间规整,解决了发音长短不一的模板匹配问题,达到语音识别的目的-speech recognition based on DTW
(系统自动生成,下载前可以参看下载内容)
下载文件列表
speech_recognition_based_on_DTW\mfcc.m
...............................\vad.m
...............................\dtw.m
...............................\enframe.m
...............................\melbankm.m
...............................\shiyan5.m
...............................\说明.txt
...............................\train_sample\9a.wav
...............................\............\0a.wav
...............................\............\1a.wav
...............................\............\2a.wav
...............................\............\3a.wav
...............................\............\4a.wav
...............................\............\5a.wav
...............................\............\6a.wav
...............................\............\7a.wav
...............................\............\8a.wav
...............................\.ext_sample\9b.wav
...............................\...........\0b.wav
...............................\...........\1b.wav
...............................\...........\2b.wav
...............................\...........\3b.wav
...............................\...........\4b.wav
...............................\...........\5b.wav
...............................\...........\6b.wav
...............................\...........\7b.wav
...............................\...........\8b.wav
...............................\train_sample
...............................\text_sample
speech_recognition_based_on_DTW