基于神经网络的说话人识别

基于VB+TTS的语音识别，可以实现简单的对话和控制，程序中使用了串口用来控制机器人的一些行为（毕业设计时做的）-VB-based TTS voice recognition, can achieve a simple dialogue and control, procedures used in the serial port used to control the behavior of some robot (design graduates do)

Linux下的CELP语言编码，压缩语音质量极好。支持2K到32K的压缩。实现部分使用C语言编写。可用做Linux下的动态库，有例子。-under Linux CELP language coding, compression excellent speech quality. Support 2 K to 32 K compression. Part of the use of C language. Linux can be done under the DLL, is an example.

一种噪声环境下连续语音识别的快速端点检测算法，格式ｖｉｐ-a noisy environment for the rapid identification voice endpoint detection algorithm format vip

改进的BP神经网络的C++源代码,可用于图象识别-Improved BP neural network C++ Source code, can be used for image recognition

语音信号的频域处理,语音虽然是一个时变、非平稳的随机过程。但在短时间内可近似看作是平稳的。因此如果能从带噪语音的短时谱中估计出“纯净”语音的短时谱，即可达到语音增强的目的。由于噪声也是随机过程，因此这种估计只能建立在统计模型基础上。利用人耳感知对语音频谱分量的相位不敏感的特性，这类语音增强算法主要针对短时谱的幅度估计。 -voice signals in the frequency domain processing, voice is a time-varying, nonstationary random process. But in a short period of time can be approximated as smooth. So if Noisy Speech from the short-term spectrum estimate "pure" voice of the short-term spectrum, and reached speech enhancement purposes. As the noise is random process, which can only be estimated based on statistical models based on. Use ear perception of voice spectrum component of the phase sensitive to the characteristics of such speech enhancement algorithms targeted at the rate of short-term spectral estimation.

录制音频功能，病可以对语音自动分频以及识别语音的浊音清音-Audio recording function, disease can be automatic voice recognition and voice-band voiced voiceless

SUN的ADPCM压缩解压程序,包括G.721,G.723,其中G.723又包括16bit,24bit,40bit的压缩解压-Sun ADPCM compression decompression procedures, including G.721, G.723, G.723 also includes 16bit, 24bit, 40bit compression decompression

matlab关于语音信号滤波处理的文章，通过matlab实现-matlab on the voice signal filtering deal with the article, through matlab to achieve

几种语音增强关于mmse算法，维纳滤波，掩蔽增强-err

60秒多段语音录放芯片APR9600.htm-60 seconds of voice recording and multi-chip APR9600.htm