GMM-apply-for-text-to-speech

这是一个小波语音降噪程序，很详细，有参考价值。(This is a wavelet voice noise reduction program, in great detail, a valuable reference.)

传统语音增强算法，谱减法和MCRC算法，matlab源代码。(Traditional speech enhancement algorithm, spectral subtraction and MCRC algorithm, matlab source code.)

基于vc++开发，dtw语音识别,MFCC参数(DTW recognice based on vc++)

自己认真修改的程序代码，并且通过测试可以运行的！对HMM-GMM的初学者有用。(Own serious modify the program code, and the test can be run. HMM-GMM useful for beginners.)

采样小波包分解语音信号，分解为3层，并求出分解系数(Speech signal using wavelet packet decomposition，decomposing 6 level，and attain decomposition coefficient)

attention model for saliency detection.

这是一个很好的频域分块自适应滤波的程序，应用于回声消除上，并与NLMS自适应滤波做了运行速度的比较,FLMS比NLMS快几十倍。(This is a very good frequency-domain block adaptive filtering procedure applied to echo cancellation, and comparison with the NLMS adaptive filter for speed, FLMS several times faster than the NLMS.)

WM8731语音芯片的驱动程序，完成录音和播放功能。主控制芯片为STM32RCT6。测试通过。(WM8731 voice chip driver to complete the recording and playback functions. The main control chip is STM32RCT6. Test pass.)

根据房间配置信息生成房间传函，进而生成模拟语音数据(Depending on the room configuration generates a room transfer function, thereby generating an analog voice data)

一种用于语音或者心音去噪和提取包络的预处理方法，对于后面信号处理更加方便(A method for denoising and extract voice or heart sounds envelope pretreatment method, the signal processing is more convenient for the latter)