yuyin

实验示例是基于语音中的mfcc，语音倒谱特征来进行聚类，先利用训练样本来计算训练样本聚类中心（用到了lbg算法），之后再进行分类。 注意：使用代码时需要自己更改文件路径。(This example is based on the MFCC in speech and the feature of speech Cepstrum to cluster. First, the training sample is used to calculate the training sample clustering center (using the LBG algorithm), then the classification is then carried out.)

语音信号的录音、读入、放音等：利用函数wavread对语音信号进行采样,记住采样频率和采样点数，给出以下语音的波形图（2.wav），wavread的用法参见mablab帮助文件。利用wavplay或soundview放音。也可以利用wavrecord自己录制一段语音，并进行以上操作(需要话筒)。 (Speech signal recording, reading, playback, etc.: the voice signal using the function wavread sampling, sampling frequency and sampling points to remember, given the following speech waveform (2.wav), wavread usage see mablab help file. Using wavplay or soundview playback. Can also record a voice using wavrecord own, and the above operation (requires microphone).)

语音信号时频分析，包括语谱图，过零率，自编的自相关，以及最后用了三种方法（短时能量和过零率、谱熵法、Teager算子）进行端点检测，代码完整且测试通过(time and frequency domain analysis of speech signals,including spectrogram,rate of zerocrossing,autocorrelation.and three method of endpoint detection,especially the Teager )

关于如何使用fpga实现语音识别 最新版本(err)

基于lms的改进型谱减法，降低噪声效果好(Improved LMS-based spectral subtraction, noise reduction effect)

语音信号去噪，在MATLAB开发环境下，对含噪声的语音信号进行卡尔曼滤波，实现语音增强的功能。(The voice signal denoising, the Kalman filter, the noisy speech signal in the MATLAB development environment Wave, speech enhancement.)

GMM说话人识别平台全套，从特征提取到模式识别，到识别率，一整套都有(GMM speaker recognition platform full, from feature extraction to pattern recognition, the recognition rate, set both)

DOA_Estimation,带有详细注释，，包含MUSIC，RootMUSIC，ESPRIT，MVDR，F-SAPES几种算法。(DOA_Estimation, with detailed annotations, contains MUSIC, RootMUSIC, ESPRIT, MVDR, F-SAPES algorithms.)

（附带有文档，文档中有方案，有程序有结果，设计完后对一段语音进行处理）给定滤波器的规一化性能指标（参考指标,实际中依据每个同学所叠加噪声情况而定）通带截止频率wp=0.25*pi。 采用窗函数法设计低通、高通、带通型FIR滤波器，对叠加噪声前后的语音信号进行滤波处理，绘出滤波器的频域响应，绘出滤波后信号的时域波形和频谱，并对滤波前后的信号进行对比，分析信号的变化；在相同的性能指标下比较各方法的滤波效果，并从理论上进行分析((With the document, document, program, program results, the design after a voice) to set the filter rules of performance indicators (reference, practice, each student adding noise may be) passband cutoff frequency wp = 0.25* pi. Window function method to design low pass, high pass, band-pass FIR filter, filtering the voice signal before and after adding noise, draw the filter frequency response plot the time-domain waveform and spectrum of the filtered signal, and filtering the signal before and after comparison and analysis of signal changes the filtering effect of the various methods in the same performance indicators, and the theoretical analysis)

这是一个语音处理工具箱，提供了语音处理的基本函数，包括有分帧、能量计算、零交叉计算、多种方法的音调提取、共振峰提取。。。等等。(This is a speech processing toolbox provides the basic function of voice processing, including one of those who frame, energy calculation, zero cross-terms, various methods of pitch extraction, formant extraction. . . And so on.)