在线签名鉴定，用AR实现算法和DTW算法实现，还包括一个比较综合的实例，对此方面研究的朋友有用处...

语音识别与合成入门2，word或压缩包中内有matlab源码-speech recognition and synthesis 2 entry, word or compressed packages within Matlab FOSS

XP Menu是一款神奇的小控件，可以将Menu和Pop-up Menu转变成Office XP风格。-XPMenu is a magic control.It can change Menu and Pop-up Menu to Office XP character.

基于分形的纹理图像的金字塔处理方法,搞分形的可以-A grain image synthesis method depend on Pyramid algorithmic. It is useful for guys doing separate shape

语音识别与合成系统. 里面有详细的介绍与程序-Speech Recognition and Synthesis System. There are a detailed introduction and procedures

语音识别专辑五- Speech recognition special edition five

一个很好的模式识别应用书籍,介绍人脸识别以及语音识别的技术-a good pattern recognition applications books, introduced face recognition and voice recognition technology

语音的正弦模型程序，用户接口比较全。包括正弦模型的分析合成，模块比较多，可以参考网上的说明。-voice sinusoidal model procedures, the entire user interface comparison. Including the sinusoidal model of synthesis, more modules, the Internet can refer to the note.

OTOMATİ K KONUŞ MA TANIMA ALGORİ TMALARININ UYGULAMALARI Kö ksal Ö CAL Ankara Ü niversitesi Fen Bilimleri Enstitüsü Elektronik Mühendisliğ i Anabilim Dalı Danı ş man : Yrd. Doç . Dr. H. Gö khan İ LK Bu ç alı ş mada, SMM (Saklı Markov Model) tabanlı izole bir kelime tanı ma sistemi geliş tirilerek, sesin akustik parametreleri LPC (Linear Predictive Coding), LPCC (LPC Cepstrum), CEPS (Ayrı k Fourier dö nüş ümü tabanlı cepstrum) ve MFCC (Mel Frequency Cepstral Coefficients) ‘nin konuş macı dan bağ ı msı z konuş ma tanı ma sistemlerindeki performansları değ erlendirilmiş tir. Değ iş ik akustik parametrelerle birlikte değ iş ik S-OTOMATİ K KONUŞ MA TANIMA ALGORİ TMALARININ UYGULAMALARI Kö ksal Ö CAL Ankara Ü niversitesi Fen Bilimleri Enstitüsü Elektronik Mühendisliğ i Anabilim Dalı Dan&

很多人不会在windows里编译htk,因此所有htk3.2.1的程序在windows里编译了一次,可以在命令窗口下直接使用这些指令.-many people will not compile the windows Lane HTK, all the procedures htk3.2.1 windows Lane compiler, the one window in order to use them under direct orders.

ETSI发布的用于研究分布式语音识别的前端降噪代码-ETSI issued for the study of Distributed Speech Recognition front Noise Code