自编的FASTICA程序，简明实用，并附带两个子程序以及WAV文件，...

HTKbook，剑桥大学语音识别工具包HTK的简历文件。PDF，有HTK的详细说明

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.

G.723.1语音压缩编码的英文原文和中文译文。该协议是双速率语音压缩编码，提供5.3和6.3kbps的速率，占用很窄的带宽。-G.723.1 voice coding the original English and Chinese translations. The agreement is a two-bit-rate speech coding, and 5.3. Rate, which takes up a very narrow bandwidth.

一个基于DirectShow的语音采集与简单识别的例子程序，主要用于机器人的简单交互。包括C＋＋源代码。-a DirectShow-based Voice Acquisition and simple identification procedures example, Robot used mainly for the simple interaction. Including C++ source code.

xvoice:linux的语音识别源码-xvoice : linux source of Speech Recognition

GSM语音压缩编码源代码] GSM语音压缩编码源代码-GSM voice compression coding source code

语音识别与合成入门4，word或压缩包中内有matlab源码-speech recognition and synthesis four entry, word or compressed packages within Matlab FOSS

用于语音识别的离散隐马尔可夫模型程序（非特定人，多个观测序列），已调试通过。-used discrete speech recognition Hidden Markov Model (non-specific, a number of observation sequence), has been through testing.

对数运算实现是32位的运算包含有指数和对数的求法 -LOG

几篇关于基音检测的论文.可以看看哈.以后还将传上来-Several papers on the pitch detection. Can look at Kazakhstan. Later will mass up