资源列表
vadandRecord.rar
- 采用端点检测的语音录音程序，端点检测采用了基于实时信息的ETSI提供的语音录音程序。,Endpoint detection using voice recording procedures, endpoint detection-based real-time information provided by the ETSI procedures for voice recording.
Sound.rar
- 一个C++的语音识别系统，可用，值得参考,Sound
VQ.rar
- 在MATLAB环境下实现基于矢量量化的说话人识别系统。在实时录音的情况下，利用该说话人识别系统，对不同的人的1s～7s的语音进行辨识。实现与文本无关的自动说话人确认的实时识别。 使用说明： 1 训练 打开Matlab 使Current Directory为VQ所在的文件夹(比如：E:\vq) 在Command windows中输入 train( 1s\ ,7) 这是将1s中的wav文件进行特征提取并产生VQ码本， 在workspace中有个ans的文件保存为.m文件，比如7.
c++code.rar
- 这个文件是一个C++语音合成源代码 就是输入一段文字 可以用它转换成语音 ,This document is a C++ Speech synthesis is the source code input section of the text can use it to convert voice
enframe.rar
- matlab 用于语音的分帧 加窗的源码,matlab for speech sub-frame of the source window
vad.rar
- 自己写的关于语音识别技术中预处理过程中端点检测技术源码，用的matlab语言,Wrote it myself on voice recognition technology in the pretreatment process endpoint detection technology source, using the matlab language
WinHTK.rar
- 著名语音识别程序HTK，可在VC环境下编译运行,Well-known speech recognition program HTK, can be compiled in VC environment to run
HTK_basic_tutorial.rar
- HMM模型应用领域很多，HTM只要是用于语音识别。这是它的basic tutorial.它是用C语言实现的开源软件,HMM model for many applications, HTM as long as it is used for speech recognition. This is its basic tutorial. It is realized by C language open source software
(wsola)audacity-src-1.3.0b.tar
- 一个开源的软件源程序，可以实现语音处理的多种效果，其中采用到wsola的算法 ,a revenue source software, voice processing can be achieved by a variety of effects, which used the algorithm to wsola
CMU-Cam_Toolkit_v2.zip
- 自然语言处理和语音识别中必须的语言模型工具，这个工具可以生成文本或者二进制格式的N-gram表。配合HTK使用效果会更好。,natural language processing, speech recognition and language model must tools, this tool can generate text or binary format of the N-gram table. With the use of HTK results will be better.
VLCWrapper
- modified VLC Wrapper for VC-modified VLC Wrapper for VC++
speaker-recognition--training
- 这个是基于SVM的说话人识别的训练训练过程，对于说话人识别很重要。-This procedure is based SVM for speaker verification training, which is so important for speaker recognition.