zengqiang

是一个语音识别的程序，有LPCC，MFCC等的代码，最后用SVM进行分类(Is a voice recognition program, there LPCC, MFCC and other code, the final classification with SVM)

这是我写的用c语言实现LBG算法的一个程序。LBG算法是语音信号处理中一种矢量量化的方法。我的邮箱：wleechina@163.com(This is what I wrote with C Language LBG algorithm a procedure. LBG is the voice signal processing a vector quantization method. My mail : wleechina@163.com)

语音合成软件，输入文字，自动生成声音文件，全部是源码(Speech synthesis software, input text, automatic generation of sound files, all the source code)

一个完整的语音端点检测MATLAB程序序，包含有完整的文件，通过调试，正确可用 (An integrated voice activity detection MATLAB program, includinng complete documentation, through testing, can be used correctly )

语音信号处理，阵列为10阵元线阵，宽带和窄带波束形成(Speech signal processing, 10 sensors of microphone linear array,Broadband and narrowband beamforming)

（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)

线性预测倒谱系数（Linear Prediction Cepstrum Coefficient,LPCC）是线性预测系数（Linear Prediction Coefficient,LPC）在倒谱域中的表示。该特征是基于语音信号为自回归信号的值设，利用线性预测分析获得倒谱系数。(Linear Prediction Cepstrum Coefficient)

一个可执行的HMM语音识别程序例程，实现了对10个数字音的识别程序，包含了HMM语音识别中的分段，MFCC特征提取，Baum-Welch训练，及Viterbi等算法，通过此例程可以很好的理解HMM的算法原理(An executable HMM-based 10 digits speech recogntion program example. this code zip file includes segmentation, MFCC feature extraction, Baum-Welch based re-estimation and Viterbi algorithm involved in HMM. it helps much better understand the HMM algorithm and its application for speech recogntion. )

在仿真语音增强时，往往需要向纯净语音中添加适当的噪声然后作仿真对比，这个程序正是实现这了个功能。(When the speech enhancement is emulation, it is often necessary to add appropriate noise to the pure speech and make a simulation contrast. This program is exactly the function of this program.)

自己用matlab编的语音合成识别程序，验证好使。(Yourself using matlab speech synthesis recognition program, verify so.)