音频特征提取

c++平台开发的可以进行text to speech软件源代码 内有详细的使用安装说明 包括freephone和wxmbrola两个模块-c++ platform that can be text to speech software source code used within the detailed installation instructions, including freephone and wxmbrola two modules

径向基神经网络Matlab编程，包含4个分厂不错的Matlab程序，读者可以下载运行一下看看。-Radial Basis Function Neural Networks Matlab programming, including 4 branch good Matlab program, readers can download to run about to see.

此程序为自相关法进行基音检测的程序，主要应用于语音识别。-program for petch detection using auto-correlation method, mainly for speech recognition

LMS滤波器（最小均方误差滤波器），学习现代数字信号处理理论的人应该用的上。-LMS filter (minimum mean square error filter), learning modern digital signal processing theory should be used on.

Android开发的语音识别系统,本设计利用Android平台使用PocketSphinx做离线语音识别，小范围语音99%识别率，非常适合做语音识别开发的人用，具有一定参考价值

自己根据网上的说明自己编写的测试TTS的程序-Own description of the basis of online tests to prepare their own procedures for TTS

The Yin algorithm was developed by Alain de Cheveigné of IRCAM-CNRS and Hideki Kawahara of Wakayama University. It allows for real-time continuous (for each sample) fundamental frequency estimation. It features a very low error rate and few tuning parameters. This implementation is a C++ template, with EMM support for faster processing. Developped in Visual C++ 6.0, but should compile with other compilers.-The Yin algorithm was developed by Alain de Cheveigné of IRCAM-CNRS and Hideki Kawahara of Wakayama University. It allows for real-time continuous (for each sample) fundamental frequency estimation. It features a very low error rate and few tuning parameters. This implementation is a C++ template, with EMM support for faster processing. Developped in Visual C++ 6.0, but should compile with other compilers.

一个很好的模式识别应用书籍,介绍人脸识别以及语音识别的技术-a good pattern recognition applications books, introduced face recognition and voice recognition technology

ica 权威paris在很久以前写的ica算法程序，稍作修改可以用于声音信号识别。-Paris, one of the authorities of ICA, created the program at long time ago. It can be used to recognise speech signal if modify a little.

AMR-WB声码器VAD（语音活动检测）程序。测试使用8kHz采样率和16位wav量化文件。