资源列表
1
- DIRECTX 进行录音功能,保存为wav格式的作用-The DIRECTX recording function
turtlebot_teleop.tar
- 基于ROS(robot operation system), 以TURTLEBOT 机器人和KINECT，通过语音控制机器人移动。-Using ROS and Kinect to control the turtlebot var voice.
Vector-quantization
- 语音识别提取特征向量后用到的矢量量化代码。含有中文注释，感兴趣的可以参考一下。-Used in the speech recognition feature extraction vector vector quantization code. With Chinese comments, interested can refer to.
Speech-Corpus
- 声语音连续语音语料库，包含用于语音识别培训和测试的数据-Voiced speech continuous speech corpus, contains the data for the voice recognition training and testing
SPHINX_3-
- 大词汇量语音识别系统，可以识别连续语音，是美国卡内基梅隆开发的开源语音识别系统，该程序用C编写，模块结构非常清晰，函数接口明了-Large vocabulary speech recognition system can recognize continuous speech, Carnegie Mellon developed open source speech recognition system, the program is written in C, the module struc
mfcc
- 语音识别用到的特征提取，c程序编写的，可以运行，输入音频文件，可以得到特征向量。-Used by the speech recognition feature extraction, you can run the c programming, input audio file, you can get the feature vector.
HMMsource
- 语音识别需要的隐马尔可夫模型训练及识别程序，已调试过，可以直接运行。可生成训练过的隐马尔可夫模型，和测试结果。用的到的可以看一下。-Speech recognition requires the hidden Markov model training and recognition procedures have been debugging, and can be run directly. Can generate trained hidden Markov model, and test
mel
- Convert Hz to Mel and Mel to Hz
CMNMFCC
- 具有去通道噪声功能全自动的梅尔倒谱系数提取.可以加载各种音频文件。-extracte Mel cepstral coefficients with function of remove the channel noise. It can load a variety of audio files.
VADMFCC
- 具有去静音段功能全自动的梅尔倒谱系数提取.可以加载各种音频文件。-extracte Mel cepstral coefficients with function of remove the mute paragraph. It can load a variety of audio files.
filter
- 利用滤波器处理音乐文件，但文件的格式要为.wav-Filter processing music files, but the file format should be .wav
wannianli
- 程序设计的万年历设计，采用C++开发环境，能运行-a C program calendar