资源列表
speechtotext
- 这是一个语音识别的源码，可以实现speech to text 的功能，需要调用speech sdk-This is the source of a speech recognition can be achieved speech to text functionality, you need to call speech sdk
qngmmpost
- GMM postior calculation the probility of the GMM,you can be given a prob from the GMM which speech you are processing,thank you
pcm
- 语音编码中A律pcm编码、译码的matlab仿真
agent1.zip
- Microsoft agent示例源程序，必须安装了Microsoft agent2.0以上
PlayMusic
- 这个文件是以C语言做的音乐播放的文件，可以播放三首歌曲
recog
- The sign language recognition to create a to store the training image, the video capture infront the user image and each sign language assign the letter the preprocessing the image then image is convert into rgg to cbcr. The image is segmented fe
mybss
- 基于最大信噪比的语音分离程序，有需要的朋友可以借鉴
lms
- 程序实现的功能是：一种改进型的LMS算法！具有收敛速度快的特点
rsfft
- 用MATLAB来实现声音信号处理的函数程序的源代码-MATLAB to achieve voice signal processing function of a program's source code
ICAsound
- Sound separation by ICA
wavelet-pujian
- 这是标准谱减算法和小波阈值降噪方法，虽然效果不太好，但是作为经典降噪方法，还是有很高的参考价值，也是此类文献引用最多的方法。-This is the standard spectral subtraction and wavelet thresholding method of noise reduction, although results are not good, But as a classic noise, or a high reference value, such litera
deletenoise
- 读入需要的语音文件（wav格式），进行频谱分析，对其加入随机噪声，然后进行降噪处理，降噪处理前后效果较佳-Need to read the audio files (wav format), spectral analysis, it added random noise, then noise reduction, noise reduction before and after treatment was better