SpecSubTD_Boll79

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)

基于svm分类器的汉语声调识别，实现了对声调四声的识别，纯净语音识别率100 ，噪声环境下识别率90 (The svm classifier based Chinese tone recognition, the four tones of tone recognition, the pure voice recognition rate of 100 , 90 recognition rate in noisy environments)

针对信号自适应chirplet分解未知参数多、实现起来比较困难的特点，文献[1]提出了一种新的chirplet分解快速算法。该算法利用计算信号的二次相位函数，得到其能量分布集中于信号的调频率曲线上的结论，此时通过谱峰检测可同时获得chirplet调频率、时间中心和幅度的估计；然后通过解线性调频技术获得其初始频率和宽度的估计，仿真结果验证了本文算法的有效性。(this code includs one method for chirplet analasis,that is used in voice and ultra-wave analasys,etc.)

在matlab平台利用GUI界面实现录音，播放。并对语音信号进行频谱分析，特定人语音识别，混响，混频等基础功能。(On the MATLAB platform, the GUI interface is used to record and play. And the speech signal spectrum analysis, specific speech recognition, reverberation, mixing and other basic functions.)

声音特征提取程序，分帧后，对于每一帧提取MFCC等特征(voice feature extraction)

验证码小识别源码程序，结合易语言位图支持库，调用易语言模块实现验证码识别。(Little recognition source code program , combined with easy language bitmap support library , call easy language module verification code recognition .)

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.)

EVRC的语音编码算法研究及仿真,及二阶固定码本搜索算法(Speech Coding Algorithm and Simulation of EVRC)

语音识别中的两种特征提取方法lpcc和mfcc，还有一个是文本无关的识别算法dtw，另外还有一个是预处理消噪部分的。共享一下，这些都是我调试过的，好用。(Speech Recognition two feature extraction methods and mfcc lpcc. There is a text-independent recognition algorithm dtw, in addition to a pretreatment is part of the noise source. Sharing that those are off the debugging and ease of use.)

语音识别开源代码 sphinx 0.8 windows版本(sphinx 0.8，ASR)