ITU

语音的消噪程序，传统普减法的改进，有效去除背景噪声-Speech de-noising process, the traditional S & P subtraction improvements, effectively remove background noise

txt2wav.rar文本语音（Text-to-Speech，以下简称TTS），它的作用就是把通过TTS引擎把文本转化为语音输出。代码示范了如何运用Microsoft Speech SDK 建立自己的文本语音转换应用程序。应该事先下载微软的语音SDK里面含微软的语音开发工具原来是sapi5.1现在好像升级了微软的MSDN上有下-txt2wav.rar text pronunciation (Text-to-Speech, hereafter refers to as TTS), its function is transforms through the TTS engine the text as the pronunciation output. How did the code demonstrate has established own using Microsoft Speech SDK text pronunciation transformation application procedure. Should beforehand download Microsoft inside pronunciation SDK to contain Microsoft the pronunciation development kit originally is sapi5.1 now looks like promotes on Microsoft s MSDN to have next

LPC 10 Code,比较经过lpc编码与没有经过lpc编码的语音差别，用自相关法计算lpc参数。-LPC 10 Code, comparison, after encoding and not LPC LPC voice coding differences, using auto-correlation method to calculate LPC parameters.

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.

实现了精简的FFT语音压缩 采取了一种新的算法有一定的参考价值-Implementation of speech compress used by simplified FFT algorithm.It is a new one,and useful to you.

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

语音识别专辑五- Speech recognition special edition five

这是语音信号处理中求倒谱的程序,我自己编的,很简单,实现了一段序列求倒谱的功能-This is the voice signal processing for cepstrum procedures, I developed, is very simple. achieve a sequence for the functional cepstrum

国际上最新的说话人识别算法的源程序，内置语音训练数据-The latest international speaker recognition algorithm source code, built-in voice training data

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.