speechrecognitionbasedonhmm

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)

目前2.4kbps的混合激励线性预测 (MELP) 语音编码方法已经被确定为美国新的联邦语音编码标准.本文提出了一种改进的MELP语音编码方法,利用滤波器相似度和基于LPC系数分类的矢量量化技术,可以把MELP的码率降到1.7kbps以下,仍有较好的合成语音质量.(An Improved MELP Speech Coder)

speech file to be analyzed Format : binary file 16 bit-samples 240 samples per frame (speech file to be analyzed Format : 16 bit binary file-samples of 240 samples per fram e)

一个对有噪声的音频信号进行自相关滤波的c程序，用的turbo c 3.0工具(One pair of noisy audio signal autocorrelation filtering c program using turbo c 3.0 Tools)

自己提取的讯飞输入法语音识别组件，可绿色运行，解压双击iFlyVoice.exe即可运行，语音识别能力比较强！(The voice recognition component extracted by Xunfei can be operated in green, decompressed and double-clicked iFlyVoice.exe can be operated, and the voice recognition ability is relatively strong!)

有趣的语音识别程序，可以利用这个程序实现语音防盗门。是根据每个人不同的声调来实现的(interesting voice identification procedures, we can use this procedure voice security doors. Everyone is different tone to achieve the)

matlab 实现的基于GMM的说话人识别系统(matlab implementation of the GMM-based speaker recognition system)

自相关函数的应用，进行基音检测，在MATLAB下进行仿真(Application of autocorrelation function for pitch detection, carried out in the MATLAB simulation)

基于倒谱短时部分反映了语音的声道特性，先用汉明窗取一帧语音，然后经变换得到语音倒谱，将倒谱短时部分取出，进行正交反变换后将得到声道的对数谱，即得到语音频谱的包络。将频谱包络和频谱画在一张图上，有很好的对比效果。获取的包络效果十分好。(Based Cepstral partly reflects the short channel characteristics of the speech, first take a Hamming window with a frame of speech, and speech cepstrum obtained by converting the cepstrum short segment out inverse orthogonal transform to obtain channel will of the spectrum, i.e. to obtain the envelope of the speech spectrum. The spectral envelope and spectral painted on a chart, there is a good contrast. Get the envelope effect is very good.)

基于espeak的一个文本转语音的代码,可以把文本转成WAV文件(basic espaeck to translate txt to wav file)