资源列表
speech
- 一篇关于混合语音说话人分离技术的英语文章,附有本人的在中文翻译
dmss7
- 7号信令开发,针对7号信令进行语音方面的开发,ivr tech-dmss7
hmm
- 此代码包含了HMM的backward算法,viterbi算法以及,前后向算法-This code includes backward,vitibi and Baum-Welch algorithm of HMM.
TTSDEMO2.0
- 微软TTS控件 语音提示效果 自动播放输入的文字-Microsoft TTS control automatically play the voice prompt enter the text effect
SpeechRecognition20101223
- 语音识别,从wav文件中读取一段音频,并识别出来显示在文本框中.基于MS Speech SDK5.1-speech recognition
TInterestingVh
- 本程序使用C语言编写,实现的的是语音识别功能。可直接使用。 -This procedure using the C language to realize that the voice rrecognition function. Complete source code can be used directly.
RSC_Series_Speech_Recognition
- RSC系列新型语音识别电路原理及其应用 主要芯片为rsc3-RSC Series New Speech Recognition Circuit Principles and Applications of the main chip rsc300
lame-3.92-ACM
- lame是公认的转换Mp3的目前最好的工具,本文件包里有lame的说明文件-lame is recognized as the best conversion tool for Mp3 present, this document is the documentation package are lame
terse-jurassic-10
- MPEG4压缩的源文件,从网上下载的,非常有用。
ldcelp-2[1].0
- ld-celp, speech coding
dssdf
- 语音功能在多参数检测仪上的实现-Voice in a multi-parameter detection apparatus of the implementation
SDHumming
- 调试通过的盛大哼唱检索系统的代码,包括特征提取和特征比对两个部分。-Grand humming retrieval system debugging through code, including feature extraction and matching two parts.