资源列表
zhongxinxuebo
- 读取语音，进行中心削波处理，可以更好的提取基音-Read the speech center clipping processing can pitch extract
enframe
- 实现了语音信号的端点检测功能，基于matlab环境，是hmm语音识别的初步工作-Voice signal endpoint detection based on matlab environment, hmm speech recognition preliminary work
hmm-matlab-platform
- 基于matlab的hmm语音实验平台，包含了众多的实验程序，为语音识别工作提供参考-Matlab-based the hmm Voice experimental platform, contains a large number of experimental procedures, and provide a reference for the voice recognition work
SparkEditor1.7
- Channel editor for Spark stb
matlab4asp
- 对语音识别技术中涉及到的知识用matlab编写了一系列源码供下载，如读取/播放wave文件，音乐信号的时域/频域波形等。-Knowledge of the speech recognition technology involves a series of source code written in matlab for download, such as read/play a wave file, the music signals in time domain/frequency dom
bss-using-mutual-information-algorithm-2
- Fetal electrocardiogram (fetal ECG) extraction is an interesting as well as a difficult problem in signal processing. This forms one important application of Independent Component Analysis (ICA) or Blind Source Separation (BSS),
voiceprint
- 声纹识别MFCC特征提取以及GMM训练过程，有界面，清晰易懂！-Voiceprint recognition MFCC feature extraction and GMM training process, interface, transparent!
change_speed
- 變速不變調，是一個能夠改變速度，卻不會變更音調的程式碼。-The same transfer speed, can change the speed, but it does not change the tone code.
VideoSynthesizer-5.0
- 这是一款非常简单的视频合成软件，可以直接导入几段视频合成，没有AE和PRE复杂，非常不错。-This is a very simple video synthesis software, can be directly imported paragraphs video synthesis, AE and PRE complex, very good.
svm-based-tone-recognition
- 基于svm分类器的汉语声调识别，实现了对声调四声的识别，纯净语音识别率100 ，噪声环境下识别率90 -The svm classifier based Chinese tone recognition, the four tones of tone recognition, the pure voice recognition rate of 100 , 90 recognition rate in noisy environments
femail
- 标准的10个数字和26个字母的女音数据源文件，用于语音信号处理-10 numbers and 26 letters of the standard the female sound data source file for speech signal processing
DTMF-RD
- DTMF解码器包用户指南，可能是有用的发展-The DTMF decoder package User' s Guide, may be useful for the development of