mfcc

语音信号处理第三版 赵力等编著 配套程序(Codes of speech signal processing 3rd.)

语音识别中信号特征的提取，基因周期估计，共振峰估计等。(Signal feature extraction in speech recognition, cycle genes estimation, formant estimation,etc)

块和子带自适应滤波器matlab源文件，内有详细说明及运行结果图(Block and Subband Adaptive Filters)

基于GMM的MFCC算法的说话人识别，Maltab的高斯混合模型，12维。(MFCC speaker recognition algorithm based on GMM)

通常语音信号在增强时会出现混响现象，演讲者为了消除背景混响，不得不频繁地偏转头部的方向，这样会造成脉冲响应的不断改变。我们结合盲解卷法和频谱消去法来提高逆滤波器的滤波效果。我们利用输入语音信号间的相关系数矩阵计算出稳定、精确的室内脉冲响应的逆滤波器，而这些输入信号无需测量室内的脉冲响应就能被观测到。逆滤波能够消除早期的反射，这些反射包含混响中的绝大部分能量。之后，用频谱消去法来抑制逆滤波后的信号的尾部混响。本方法在实际适应性方面的表现通过具体的实验进行了验证，结果表明盲解卷法和频谱消去法的结合相较于单独使用一种方法，能够提供一个更优越的演说环境。(Usually voice signal will be enhanced when the reverberation phenomenon, the speaker in order to eliminate the background reverberation, and had to frequently deflect the direction of the head, this will cause the impulse response of changing. We combine the blind deconvolution and spectral elimination method to improve the filtering effect of the inverse filter. We use the correlation coefficient matrix between the input speech signal to calculate the stable, accurate inverse filter of the indoor impulse response, and these input signals do not need to measure the room impulse response can be observed. Inverse filtering to eliminate early reflections, these reflections contains most of the energy in the reverberation. After the spectrum elimination method to suppress the tail reverberation of the signal after the inverse filtering. Performance in the actual adaptation of the method by specific experimental validation results show that the blind deconvolution and spectrum to eliminate )

用自相关函数提取语音信号基频，提取音频文件的基频等高线(Use the autocorrelation function on segments of the signal (windowsize: 100ms) and compute the fundamental frequency. Use a max_time_lag of 100ms in the autocorrelation function and a window shift of 25ms. Create a fundamental frequency vector and plot the pitch contour.)

使用子带谱熵进行的端点检测，将谱熵分为几个子带，检测效果不错(The use of sub-band entropy of the endpoint detection, the spectral entropy is divided into several sub-band to detect the effect of good)

用三种经典的方法对语音信号进行增强，效果还不错并且三种方法的比较(With three classical methods of speech signal enhancement, the results were good and Comparison of Three Methods)

基于MFCC的GMM的说话人识别，是很好的语音处理程序(MFCC of the GMM based speaker recognition, speech processing is a very good program)

attention model for saliency detection.