cochleagram.tar

语音识别，实现语音的识别功能，，特定人的语音识别。识别0~9的发音(Speech recognition, voice recognition function, a particular person' s speech recognition. Identify the pronunciation of 0 to 9)

利用自相关或平均幅度差提取基音原理，帧长160，帧移80。求能量E、过零率Z和基音周期pitch；采用自相关法或平均幅度差法求取基音周期，基音周期范围（80~400hz）；画出能量、过零率和基音曲线。(Pitch principle is extracted by means of autocorrelation or mean amplitude difference)

C# 对接 Java 3des md5WithRsa, 有需要的可以参考下(If you need C # to dock Java 3des md5WithRsa, you can refer to the following)

GMM的说话人识别系统，识别效果90 多(GMM speaker recognition system, the recognition effect more than 90 )

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)

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)

用MATLAB来实现谱减法降噪。有源程序和降噪先后的语音信号，有实验的结果图(Use MATLAB to achieve spectral subtraction noise reduction. There has voice source and noise signals, there are experimental results of Figure)

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)

matlab代码，语音的压缩和编码，主要利用了心理声学模型，得到低比特编码 和高质量语音(matlab code, voice compression and coding, psychoacoustic model used by low-bit encoding and high-quality voice)