ETSI发布的用于研究分布式语音识别的前端降噪算法

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.

本文分析了用经验模态分解( Empirical Mode Decomposition ,EMD) 方法处理非平稳噪声信号的基本原理 , 并利用 EMD 方法有效地消除了高斯白噪声对瞬态散射回波的干扰. 文中以一人工合成瞬态回波为例 ,对本方法的有 效性作了检验.-This paper analyzes the use of empirical mode decomposition (Empirical Mode Decomposition, EMD) method to deal with non-stationary noise signals in the basic principles and methods of use of EMD effectively eliminates the Gaussian white noise on the transient scattering echo interference. Text in one artificial Synthesis of transient echoes as an example of the effectiveness of this method were tested.

基于matlab的自适应仿真，其算法都是LMS算法，有系统辨识，噪声对消，自适应滤波器，陷波器，图像的DCT变换-adaptive emulation based on LMS,include system recognise,noise canceler,adaptive filter,dct transform

首先对语音信号的预处理和特征提取问题进行了讨论,提取了三个有效的语音识别特征参数—LPC系数、LPC倒谱系数和Mel频率倒谱系数(MFCC);其次着熏讨论了语音识别中常用的两种识别方法—基于模板匹配的DTW和基于统计膜型的HMM在语音识别中的应用,分别讨论了各自的模型训练和识别的方 法,对HMM在实际应用中的一些具体问题也进行了讨论;最后对常规HMM提出了一些改进方法,包括显式状态驻留和随机分段模型(SM),重点讨论了SM在 语音识别中的训练和识别方法,并通过一个孤立数字语音识别系统验证了其比常规HMM更能描述语音信号的特征。

用VC编的用于显示语音的波形图，可以将microphone中的语音波形显示促。是自动的显示程序。-VC series of the show for the wave of voice, the microphone to voice waveform display promoting. The show is automatic procedures.

用Delphi写的呼叫中心-Call Center in delphi programming

自编的联合对角化程序，简单，清晰，并有痃详细的注解，带有两个波形文件，可直接显示结果。-jointly staged by the diagonalization procedure, a simple, clear and detailed explanation feast, with two waveform documents, The results can be shown directly.

使用MATLAB编写的nlms滤波器程序代码！-Prepared using the MATLAB program code nlms filter!

OPNET wireless_mrt_net_ref-antenna_test-OPNET antenna_test

一个语音控制系统的源代码，需要调用matalab库-A voice control system source code, need to call the Treasury matalab