资源列表
ztnorm
- 对于说话人语音识别得到的分数，先进行2次znorm规整，再做一次tnorm的规整化，使得分数更加合理。-Speaker voice recognition score, the first 2 times znorm structured, do it again regularization tnorm, more reasonable scores.
MeterDlg
- （第一部分）混音函数演示程序， VC源码-多媒体-,由于网速太慢了，我这里只有分成几次上传了啊-(Part I) mixing function demo program, VC Source- Multimedia-, due to slow speed, I here only divided into several uploaded ah
stdafxc
- （第五部分）混音函数演示程序， VC源码-多媒体-,由于网速太慢了，我这里只有分成几次上传了啊-(Part V) mixing function demo program, VC Source- Multimedia-, due to slow speed, I here only divided into several uploaded ah
CASourceGrabber
- this program can capture the source from the microphone in window mobile or other windows platform. it use a fundamental wave library in windows such as WaveIn-this program can capture the source from the microphone in window mobile or other windows
dtwtest
- 一个测试dtw算法的程序，A program test the dtw-an algorithm testing procedures, test the A program dtw
sdsds
- 小波变换在图像处理中的应用 用小波变幻的方法去除噪声-wavelet transform in the image processing applications using wavelet changes in the method of removing noise
pitch
- 用于提取基音，适用于学习和研究语音方向的专业人员-Used to extract pitch, learning and research for professional voice directions
endPointDetect
- 用于语音的端点侦测，特别是当声音比较嘈杂或者录音设备的质量不好的时候，能够自动适应环境，切分出有效的声音。-for speech endpoint detection, especially when the voice is relatively noisy or recording equipment of poor quality, can automatically adapt to the environment, to separate an effective voice.
pitch
- 基音检测，通过计算最大值，检测其位置，再检测零值的位置来实现.-Pitch detection, by calculating the maximum and its position, and detect the position of zero.
martin2001.zip
- 经典噪声估计，用于speech enhancement,noise estimation algorithm in speech enhancement
C
- HMM的c语言详细实现过程，以及hmm的思想介绍和实现-HMM and c language implementation process in detail，And hmm, introduction and implementation
DTMF-ASM
- dtmf解码程序的源文件，效率很高。做音频分析和需要解码dtmf的朋友需要。-dtmf decoding program source files, with high efficiency. And friends need to decode dtmf need to do audio analysis.