语音识别中对声音的处理，端点检测的简单方法，利用ME做端点估计。...

TI 的回声抵消编程 Guide，详细介绍了 echo cancellation 的流程 并附有 C 编写的源代码-TI s echo cancel pragramming guide, it introduced the flow of echo cancellation in detail and also attached with the source code written in c.

关于SDK的 语音识别和语音合成的代码。 可以试试啊-On the SDK Speech Recognition and Speech Synthesis code. Try ah

语音合成 变速不变调 变调不变速 且每行都有注释 适合学习-The same tune speech synthesis speed transmission and the modulation is not suitable for learning each line has a comment

这是语音识别的几个程序，包括语音的特征提取、端点检测的程序。-This is the number of speech recognition procedures, including the voice feature extraction, endpoint detection procedure.

SoundRuler是一个用来分析和图形化重复声音的工具(生物声学)。它识别和测量文件中每种声音的时间和光谱属性。执行的结果可以保存到电子数据表，也可以导出波形图。-SoundRuler is uses for to analyze and the graph repetition sound tool (biological acoustics). It distinguishes and surveys in the document each kind of sound time and the spectrum attribute. The execution result may preserve the electronic data sheet, also may derive the oscillogram.

LPC10 2.4Kpbs 语音压缩定点运算C语言源程序OPENLPC-Voice compression LPC10 2.4Kpbs computing fixed-point C language source code OPENLPC

语音控制小车的源码，很不错，可以识别声音，自动完成前进倒车等-Voice-controlled car source, it is good to identify the voices of forward to reverse, such as auto-complete

MATLAB波形工具箱。将工具箱文件夹添加到命令窗口中的MATLAB路径类型main

利用倒谱求出语音信号频谱包络和基音频率。-Cepstrum was calculated for the spectrum envelope of speech signal and the pitch frequency.

基于HTK的命令字语音识别系统，将对10个命令字进行识别，它们分别是：开机，关机，升温，降温，制热，制冷，强风，弱风，摆风，静止。 语料的构成包括训练级23个人，每个人按顺序说这10个命令字3遍；测试级6个人，每个人按顺序说这10个命令字3遍。其中还要注意停顿和结束时的静音识别。我们要对所有的预料进行训练，最后得到识别的结果。