资源列表
recorder
- Jrecorder录音 支持语音识别，并且将语音信息上传到服务器，服务器端进行识别-Jrecorder
blind-speech-separation
- 完成欠定盲语音分离，源信号为3路输入，有2路麦克风，用c实现。-Underdetermined blind speech separation is completed, the source signal is 3 inputs, 2 mic, with c achieve.
ISM
- 产生房间脉冲响应的源代码，在多噪声，多混响的情况下，信噪比很低，信干比也很低，同时伴随着噪声是非平稳的情况。-room impluse response
SVM_One_Class
- 基于单类SVM的说话人语音分割的算法源程序-Based on one-class SVM speaker segmentation source code
speech-recognition-by-vikky
- this a matlab code for speech recognition using discrete wavelet transform. code is working very well and good for future research work.-this is a matlab code for speech recognition using discrete wavelet transform. code is working very well and good
codes-for-DWT-based-speech-recognition
- this a matlab code for speech recognition using discrete wavelet transform. code is working very well and good for future research work.-this is a matlab code for speech recognition using discrete wavelet transform. code is working very well and good
rec
- Recognition facial images in an important step in computer vision
wavenengliang
- 小波分析语音信号并计算各IMF包络的能量熵-Wavelet analysis of vibration signals and calculate the energy entropy IMF envelope
wav file read using vc6.0
- reading and write a wav file using vc6.0
sphinx3-0.4.1
- sphinx系统是一个拥有悠久历史的语音识别系统，李开复自称第一个sphinx是他写的。 传说 中是第一个实用的10数字语音系统。 是由卡奈基.美隆大学研发。 sphinx3.x是基于C语言的最新版本,sphinx和 sphinx2请大家不要去研究了。 sphinx for ppc是一个在PocketPc上实现的嵌入式语音识别系统。 而 sphinx4是完全用JAVA编写实现的语音识别系统， 因为JAVA的特性，在平台间移植
CMUseg_0.5.tar
- CMU的语流切分工具，运行于linux环境下，老货很难得了。-CMUseg 0.5 This directory contains the binaries, source code and segmentation scr ipt for the CMUseg Waveform Segmentation package. Precompiled binaries include the DEC OSF1, HPUX, LINUX and SUN architectures.
ViaVoiceSDK
- ibm语音识别软件viavoice 的sdk开发包，现在很难见到了。-ibm voice recognition software viavoice the sdk development kit, it is difficult to see it.