KDE下支持语音输入控制命令输入的东东

g.729的实现，应用于ip电话通信等很多需要语音压缩的地方，是国际电信联盟itu应用最广泛的一种标准之一-G.729 the realization used ip telephony and many other needs of the local voice compression, the International Telecommunication Union ITU is the most extensive application of a standard one

Rls算法源程序2 采用更新的自适应算法，实现滤波功能。-Rls algorithm source code 2, using the updated adaptive algorithm filtering.

文字阅读器，运行前须安装speechsdk51.exe和speechsdk51LangPack.exe语音引擎，在微软网站上可以下载到。-text reader, prior to the operation and installation speechsdk51.exe speechsdk51LangPack.exe voice engine, the Microsoft Web site to download.

lms的matlab程序仿真，可以实现lms的一些性能仿真-matlab simulation of LMS procedures, you can realize some of LMS performance simulation

converts text written by you to speech . require microsoft API.

这是用vc++编写的程序,在语音识别中经常用用到,是语音识别的第一步:time alignment. 分别用两种方式完成:1.非递归2.递归-This a vc++ program which is useful in voice recognizing and it is also the basic of the voice recognizing .I use two ways to accomplish it:1 nonrecursion 2.recursion

基于GMM的概率神经网络PNN具有良好的泛化能力，快速的学习能力，易于在线更新,并具有统计学的贝叶斯估计理论基础，已成为一种解决像说话人识别、文字识别、医疗图像识别、卫星云图识别等许多实际困难分类问题的很有效的工具。而且PNN不但具有GMM的大部分优点，还具有许多GMM没有的优点，如强鲁棒性，需要更少的训练语料，可以和其他网络其他理论无缝整合等。-GMM based probabilistic neural network PNN good generalization ability, the ability to learn fast, easy online updates, and with the Bayesian statistical theory based on estimates, and has become a solution as speaker recognition, text recognition, medical image recognition, satellite images and other real recognition when difficulties classification of very effective tool. But GMM PNN is not only the most advantages, but also has many advantages GMM not as strong robustness, require less training corpus, and other networks to other theories, such as seamless integration.

线性量化。读取WAV文件，用不同的比特数量化，抽样频率在8khz-Linear quantization. Read WAV files, with different number of bits, the sampling frequency of 8kHz

语音识别专辑四- Speech recognition special edition four

我新下载到的一个语音工具包，不知道大家看没看过，所以传上去跟大家共享一下-I downloaded the new voice of a tool kit, I do not know if you do not read, follow-up share what