-
chxu
本程序用于测量增强语音与纯净语音的对数谱距离,用于语音增强。对数谱距离越小,表明增强语音与纯净语音越接近,增强语音质量越好;反之,则增强语音质量越差。(Calculates the average log-spectral distance between CLEAN and NOISY
signals. Frames are 25ms long with 60 percent (15ms) overlap, hamming
windowed. RS is the remove silence option (default: 0) if 1, the program
uses a Voice Activity Detector to find non-speech frames and eliminates
them from calculation of LSD. FS is the sampling frequency (Default
10KHz). )
- 2020-10-08 17:27:36下载
- 积分:1
-
MATLAB-LECTURE
麻省理工学院introduction to matlab课程作业指导,包含matlab讲义,相互交流(excellent matlab exercises homework for improving matlab same as before)
- 2015-01-15 15:27:42下载
- 积分:1
-
tianxianfangxiangtuchengxu
天线方向图程序,有些难,对深入学习有一定帮助(Antenna Pattern procedures, and some hard-depth study of some help)
- 2008-05-30 21:25:29下载
- 积分:1
-
DIY-FSK-coherent-demodulation-model
说明: 自己用simulink搭建的FSK相干解调模型(有误码率分析)欢迎改进和交流
(Own use to build the FSK coherent demodulation simulink model (with bit-error rate analysis) welcomed the improvement and the exchange of)
- 2009-08-30 19:04:18下载
- 积分:1
-
gps-signal-autocorrelation
gps信号的自相关,以及boc信号的自相关(gps signal autocorrelation, and boc autocorrelation)
- 2020-07-01 10:40:02下载
- 积分:1
-
INDUCTION_MOTOR_AND_MLI
INDUCTION MOTOR and Inverter fed Voltrag with MLI commande MAX STEP SIZE : 0.00001
- 2015-04-07 18:28:50下载
- 积分:1
-
chap_02
电子工业出版社翻译Sangjit K.Mitra的数字信号处理课本源程序(Electronic Industry Press Translation Sangjit K. Mitra Digital Signal Processing source textbooks)
- 2010-10-26 21:47:03下载
- 积分:1
-
SOR
用SOR迭代法求解方程组的解的matlab程序(With SOR iterative method to solve the solution of system program)
- 2012-03-26 15:37:27下载
- 积分:1
-
st
说明: C语言源代码,用于计算S变换,进行时频分析(S transform C language source code)
- 2015-03-30 15:52:35下载
- 积分:1
-
径向基函数神经网络的优点 RBF_NN_MIC
说明: 径向基函数神经网络的优点:逼近能力,分类能力和学习速度等方面都优于BP神经网络,结构简单、训练简洁、学习收敛速度快、能够逼近任意非线性函数,克服局部极小值问题。原因在于其参数初始化具有一定的方法,并非随机初始化。代码为RBF的matlab程序,可以使用但是需要自己配置数据。(Radial Basis Function Neural Network (RBF-NN) has the advantages of better approximation ability, classification ability and learning speed than BP Neural Network (BP Neural Network). It has simple structure, simple training, fast learning convergence, and can approximate any non-linear function to overcome the local minimum problem. The reason is that its parameter initialization has a certain method, not random initialization.)
- 2020-06-15 22:40:02下载
- 积分:1