我是做语音识别的，这是我做的一个关于端点检测的小程序，里面还有一个工具包...

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-Online signature identification, use AR to achieve algorithm and DTW algorithm, but also a more comprehensive example of this research useful friends

这是一个的matlab的对语音处理文件。、 包括录音，MFCC特征，VQLBG法的库的形成，与非特定人的识别问题。-This is one of the matlab files for voice processing. , Including the recording, MFCC characteristics, VQLBG law, the formation of the Treasury, with non-specific identification of people.

将语音录放的程序。涉及到声卡的通道。希望给大家方便 -voice recorders procedures. Relate to the audio channel. We hope to facilitate the

一个mp3的解码程序，c语言实现。其中只对layer III 进行解码。-A program of mp3 decode,programmed by c language.It can only decode layer 3.

采用LMS算法的频域均衡技术研究,lms在频域均衡方面的应用。-LMS algorithm using frequency domain equalization technology research, lms balance in the frequency domain applications.

语音识别中经典的HMM算法，包括产生序列、测试和参数训练，由C语言编写。- In speech recognition classical HMM algorithm, including has the sequence, the test and the parameter training, compiles by the C language.

This code is used to calculated Pitch of the input signal.

不定长信号合并，％执行信号相加： y(n) = x1(n)+x2(n) ％调用方式：[y,n] = sigadd(x1,n1,x2,n2) ％ y：叠加后的信号序列的序列号，包括n1和n2 ％ x1： 第一个信号序列，序列号为n1 ％ x2：第二个信号序列，序列号为n2(n2可以与n1不同)-Indefinite long-Signal merger, add up to the implementation of signal: y (n) = x1 (n)+ X2 (n) call the way: [y, n] = sigadd (x1, n1, x2, n2) y: Superposition signal sequence after the serial number, including the n1 and n2 x1: the first signal sequence, the serial number for n1 x2: the second signal sequence, the serial number for n2 (n2 with n1 different)

时域波形、短时能量、短时平均幅度、短时过零率、短时过电平率-Time-domain waveform, short-term energy, short-term average rate, short-term zero crossing rate, short-term rates over Level

一个用delphi制作的agent的动画演视-Produced by an agent using delphi animated speech, as