KDE下支持语音输入控制命令输入的东东

最后打包版本小错误，来源新的实验包，音箱命名的任务，正在进行的会议系统，javaCV（OpenCV在JAVA）的测试，电话diarization（ANR项目MEDIA）。LIUM_SpkDiarization-4.2.jar，包含一个完整的jar文件，准备使用的编译版本，包括所有的类（LIUM_SpkDiarization和外部类）和GMM资源（Java的1.6）另外，下载LIUM_SpkDiarization-4.2.src.tgz gzip压缩的tar

TI G.729A编码器和解码器的代码具有良好的实施。此代码在DSP套件和定义sotware无线电测试了很多次。g.729a TI encoder and decoder code with good implementation. This code is tested many times on DSP kit and sotware defined radios.

Intercom 是一个 Unix系统上灵活的语音传输软件。支持标准音频压缩比如GSM, G.711, and G.72x和其他音频编码。Intercom专为高速网络设计来传输高品质的语音，也支持窄带传输-Intercom is a Unix system flexible voice transmission software. Support audio compression standards such as GSM, G.711, and G.72x and other audio coding. Intercom specifically designed for high-speed network to deliver high-quality voice, also support narrowband transmission

一个通过语音控制电脑动作的程序,使用到了微软speech sdk.在微软智能代理（Agent）技术上，整合了语音合成和语音识别技术.-A computer through voice control action procedures, the use of the Microsoft speech sdk. In Microsoft Agent (Agent) technology, the integration of speech synthesis and voice recognition technology.

此文件为martin谱减法的matlab程序以及自己加入的中文注解，希望对研究martin的算法的同学有帮助-This document is for martin s matlab spectral subtraction procedures, as well as adding their own comments in Chinese, I hope the study of algorithms for martin help students

SAPI SDK是微软公司免费提供的语音应用开发工具包，这个SDK中包含了语音应用设计接口（SAPI）、微软的连续语音识别引擎（MCSR）以及微软的语音合成（TTS）引擎等等。目前的5.1版本一共可以支持3种语言的识别 (英语，汉语和日语)以及2种语言的合成（英语和汉语）。SAPI中还包括对于低层控制和高度适应性的直接语音管理、训练向导、事件、语法编译、资源、语音识别(SR)管理以及TTS管理等强大的设计接口。

验证过的最稳定的G.729A愿代码. 用于WINDOWS-Tested the most stable G.729A is willing to code. Used for WINDOWS

录音部分是参照vckbase的录音api代码,结合了一小段socket(TCP)就可以用来单方说话录音了,程序分两部分一部分是(录音机+网络发送代码),一部分是(接收数据+播放波形音乐代码),由于程序只是为了自己用,很多地方没有注意错误的识别,结构也比较乱,本程序当初最头疼的就是控制损耗内存,结果用了双缓存来存储波形数据来交替的存储/清除. -part of the recording light vckbase recording api code combination of a small socket (TCP) can be used for recording a unilateral words, part of the procedure is divided into two parts (recorders network code), part of the (receiving data waveform music broadcast code), as a result of procedures only for their own use. many places no attention to the wrong identification, the structure was chaotic, most of the first procedure is a headache for the control of memory loss, Results of the double-caching to store waveform data to the turn of the storage/removals.

语音信号处理工具包，是日本的一个大学开发的，对于HMM模型的建立很有帮助。-A tool box of speech processing, exploited by a Japanese university. It s quite helpful for setting up a HMM model.

本课题为给语音识别系统提供语音信号端点检测的功能，对语音信号端点检测进行了探讨和研究,主要是侧重语音区间的端点检测...(附软件源码)-Voice Active Detection (VAD) is discussed in this project. Detection between speech section and speechless section and emphasized.(code available).