资源列表
mfc
- mfcc c++ code This program is free software you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation either version 2 * of the License, or (at your option) any later -
spro-3.2
- Speech PROcessing tools. First edit the makefile to match your needs
yaafe-v0.64
- *Yaafe* source code should compile on *linux* and *MacOsX* platform, and uses CMake as compilation tool.
GMM-MFCC
- 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
phone
- 可显示来电归属地,可根据声音来显示0-9,可以将拨号记录-the phone has a greet job to shou the figer and record
button
- 识别0-9,有记录的功能,还可以先市地名-good is for 0 to 9 translate
Histogramequalization
- Matlab code for Histogram Eqalization
jiyinzhouqi
- 利用短时自相关分析的方法先求得基音周期,同时画出此时的基音周期走势图;然后对超出基音周期均值的1/5的基音周期点进行去除,再利用中值平滑方法剔除野点,同时对剔除野点后的基音周期点进行绘图,同时求得平均的基音周期。文件中附带实验语音,可验证。-By using the method of short time autocorrelation analysis first pitch is obtained, at the same time draw the pitch at this time
anglecos
- 利用夹角余弦距离进行样本数据分类。实现步骤主要分为以下两部分:a、待测样品X与训练集里每个样品Xi的距离采用夹角余弦距离公式计算。b、循环计算待测样品和训练集中各已知样品之间的距离,找出距离待测样品最近的已知样品,该已知样品的类别就是待测样品的类别。-Using the sample data classification Angle cosine distance.Implementation steps are divided into the following two parts: a,
DTW-algorithm
- 基于DTW算法的语音识别原理与实现,相关论文及Matlab实现流程-The principle and implementation of speech recognition based on DTW algorithm, the relevant papers and Matlab implementation process
pocketsphinx-android-demo.tar
- pocketsphinx5 prebeta的android使用例程,演示如何进行语音识别及训练-Pocketsphinx5 prebeta Android use routines, demonstrates how speech recognition and training
daopu
- 浊音倒谱图的matlab实现,包括语音信号的分帧、加窗,取一帧进行分析。-Dullness inverted spectrum realize the matlab,ncluding sub-frame of the speech signal, windowing, take a frame for analysis