fpga_shiyanjiaocheng

这是一个与语音识别与端点检测有关的文件,是用C++写的源程序,相信对大家有用(This is a speech recognition with the Endpoint Detection of the documents are written in C source files, it may be useful to think)

评书,语音小说下载程序,修改一下可批量下载(Storytelling, voice novels download, modify available for bulk download)

马尔科夫模型代码，包括连续马尔科夫和离散马尔科夫(HMM code,CHMM DHMM)

本书系统地阐述了语音信号处理的原理、方法、技术和应用，同时给出了部分内容对应的MATLAB仿真源程序。全书共12章，第1章至第7章是基本理论部分，包括语音信号的数字模型、语音信号的短时时域分析和频域分析、语音信号的同态处理、语音信号线性预测分析和矢量量化；第8章至第12章是应用部分，包括语音编码、语音合成、语音识别、语音增强和语音处理的实时实现。本书内容全面，重点突出，原理阐述深入浅出，注重理论与实际应用的结合，可读性强。(This book describes the speech signal processing principles, methods, techniques and applications, and gives the corresponding part of the contents of the MATLAB simulation source. The book is 12 chapters, Chapter 1 to Chapter 7 is the basic theoretical part, including voice signal digital model, speech signal analysis in time domain and frequency domain analysis, speech signal homomorphic processing, speech signal analysis and linear prediction vector quantified Chapter 8 to Chapter 12 is the application of parts, including speech coding, speech synthesis, speech recognition, speech enhancement and voice processing, real-time implementation. The book is comprehensive, focused and Rationale layman, focusing on the combination of theory and practical application, readable.)

基于麦克风阵列的声源定位一维music算法源代码(Based on the microphone array beamformer one-dimensional music algorithm source code)

熵值越大则每个符号包含的平均信息量越大。有研究发现，在有噪声的语音信号中，语音信号的熵和噪声信号的熵存在着较大的差异，对噪声信号来说在整个频带内分布相对平坦，熵值小，语音信号集中在某些特定频段内，熵值大。因此利用这个差异可以区分噪音段和语音段。(The greater the entropy is, the greater the average information of each symbol is. It is found that, in noisy speech signals, the entropy of speech signals and the entropy of noise signals are quite different. For noisy signals, the distribution is relatively flat in the whole frequency band, and the entropy value is small. The speech signal is concentrated in some specific frequency bands, and the entropy value is large. So the difference can be used to distinguish the noise segment and the speech segment.)

C语言实现的端点检测,具有良好的效果,对于做语音识别者来说，是很好的参考(C language implementation of endpoint detection, with good results)

绘制语音信号的 WVD 分布，对时频工具箱中的 tfrwv 及 tfrspwv 函数的使用进行了详细说明(The way of drawing speech signals WVD was shown in the m file, and corresponding functions tfrwv and tfrspwv were discussed thoroughly.)

通过广义互相关法求时延 三种加权系数 ROTH SCOT PHAT(Delay by the generalized cross correlation method)

语音识别需要用到的函数，在你的程序中可直接调用工具箱中的函数(Needed by the voice recognition function in your program can directly call the functions in the toolbox)