资源列表
HTK-3.4.1
- this is HTK Toolkit used for speech recognition
Mfccvq
- 语音识别中提取mfcc特征矢量和矢量量化的c程序-Mfcc speech recognition to extract feature vector and the vector quantization process of c
microphone1
- 基于麦克风阵列的语音增强算法研究.nh 硕士毕业论文-Based on microphone array speech enhancement algorithm. Nh master' s thesis
ORLimages
- 人脸识别中经常用到的orl数据库，库大小是每人10幅，共有40人的人脸图像-Face Recognition frequently be used orl databases, database size is 10 per person, a total of 400 face images
toolbox_dimreduc
- This toolbox is an educational and recreative toolbox around recent ideas in the field of dimension reduction. * PCA : classical Principal Componnent Analysis (linear projection). * Nonlinear dimensionality reduction by locally linear embedding
DTWc
- 本资料给出了如何用C语言编写基于DTW算法的语音识别系统,对于语音识别学习者有很大的帮助-This information is given how to use C language DTW algorithm based on voice recognition systems, speech recognition for the great help learners
voice_identify
- 语音识别源代码，可以基于它实现声音控制装置。-Speech recognition source code, it can be based on the realization of the sound control device.
work
- 求取特征参数的fisher比， -fisher ratio fisher ratio fisher ratio
PSOLA
- 基于C++的语音歌唱合成系统，核心转换为psola转换-C++-based singing voice synthesis system, the core is converted to psola conversion
shiyan
- 使用VC++ 基于MFC的小程序 能实现基本的语音识别 和语音合成功能，载入xml文件-VC++ based on the use of small MFC program to achieve the basic speech recognition and voice synthesis functions, loading xml document
MATLAByysb
- 用MATLAB进行语音识别的特征参数提取，其中包含了lpc和MFCC两种方法，并且测试通过。-Using MATLAB to carry out speech recognition feature extraction, which contains two methods lpc and MFCC, and the test.
F2_6764
- 端点检测是指用数字处理技术来找出语音信号中的各种段落（如音素、音节、词素、词等）的始点和终点的位置。语音段起止端点检测是语音分析、语音合成和语音识别中的一个必要环节。传统的端点检测方法是从wav文件中获取语音采样，将其分帧并计算短时能量和过零率参数，然后进行端点检测。这种工作方式被称为离线处理方法 ，无法实现语音信号的实时处理，对于语音信号分析具有一定的局限性。本文通过开发ActiveX控件，在MATLAB环境下将其嵌入到figure窗口中，以GUI程序的方式使用，实现语音信号端点检测的实时处