-
MSKBHN
simple simulink model of MSK
- 2010-10-21 13:55:00下载
- 积分：1
-
score
对获得的512维小波特征进行了PCA降维处理，将特征空间降至100维，并采用前面得出的最佳系数针对多项式核函数和高斯径向基核函数(On access to the 512-dimensional wavelet features to reduce the dimension of the PCA, will feature space to 100 dimensions, and using the best coefficients obtained for the previous polynomial kernel function and Gaussian radial basis function)
- 2011-04-30 11:32:18下载
- 积分：1
-
Hmm
语音识别技术的最终目标是要让计算机能与人自由交谈。目前，连续语音识别技术正趋于成熟，语音识别也延伸出了诸多实用化的研究方向。今后，语音识别的重点将集中在自然话语识别与理解、实时语音识别和语音识别鲁棒性等方面。作为一门交叉学科，语音识别所涉及到的技术有信号处理、模式识别、概率论和信息论、发声机理、听觉机理和人工智能等。(The ultimate goal of speech recognition technology is to make computers and allowing others to speak freely. At present, continuous speech recognition technology is maturing, voice recognition is also extended out a lot of practical research directions. In the future, speech recognition will focus on Spontaneous Speech Recognition and Understanding, real-time speech recognition and speech recognition robustness and so on. As an interdisciplinary subject, speech recognition technology involved in a signal processing, pattern recognition, probability theory and information theory, vocal mechanism, hearing mechanism and artificial intelligence.)
- 2010-12-27 23:33:29下载
- 积分：1
-
Elman
Elman神经网络：Elman网络是 J. L. Elman于1990年首先针对语音处理问题而提出来的, 它是一种典型的局部回归网络( global feed for ward l ocal recurrent)。Elman网络可以看作是一个具有局部记忆单元和局部反馈连接的前向神经网络。Elman网络具有与多层前向网络相似的多层结构。它的主要结构是前馈连接, 包括输入层、 隐含层、 输出层, 其连接权可以进行学习修正 反馈连接由一组“结构 ” 单元构成,用来记忆前一时刻的输出值, 其连接权值是固定的。在这种网络中, 除了普通的隐含层外, 还有一个特别的隐含层,称为关联层 (或联系单元层 ) 该层从隐含层接收反馈信号, 每一个隐含层节点都有一个与之对应的关联层节点连接。关联层的作用是通过联接记忆将上一个时刻的隐层状态连同当前时刻的网络输入一起作为隐层的输入, 相当于状态反馈。隐层的传递函数仍为某种非线性函数, 一般为 Sigmoid函数, 输出层为线性函数, 关联层也为线性函数。(Elman neural network: Elman JL Elman network is first proposed for speech processing problems in 1990. It is a typical local regression network (global feed for ward l ocal recurrent). Elman network can be seen as having a forward neural network of local memory unit and local feedback connections. Elman network has a multi-layer multilayer structure similar to the network. Its main structure is a feedforward connection, comprising an input layer, a hidden layer and output layer, which can be connected right learning correction feedback connected by a set of " structural" units, the output value of the memory for the previous time, which connection weights are fixed. In such a network, in addition to ordinary hidden layer, there is a special hidden layer, called an associative layer (or contact layer unit) this layer receives feedback signals the hidden layer, each hidden layer node has an associated layer node corresponding connection. The role of the associated layer is fo)
- 2015-03-26 22:36:26下载
- 积分：1
-
2008_bmvc_FaceDetector_demo
2008_bmvc_FaceDetector, 2008新提出一种人脸检测算法(2008_bmvc_FaceDetector, face detection algorithm, )
- 2011-10-25 16:38:43下载
- 积分：1
-
i_DBF
数字波束形成，更改指向，更改阵元数量，加噪声(DBF beam forming
)
- 2015-12-23 17:34:11下载
- 积分：1
-
jisuanjifangzhen
用于计算机仿真的若干使用程序，已检测，均正确(Use of computer simulation for a number of procedures, has been detected, are correct)
- 2011-05-01 21:37:09下载
- 积分：1
-
C_Classical-algorithm
经典算法 虽然小，但是经常用到。尤其是有的时候面试(Classical algorithm may be small, but often used. Sometimes the interview, especially)
- 2011-05-18 11:23:09下载
- 积分：1
-
m_build
以一个简单的例子说明模拟退火算法的思想 联合开发网 - pudn.com
- 2012-05-19 21:45:07下载
- 积分：1
-
psk
PHASE SHIFT KEING MODULATION TECHNIQUE FOR COMMUNICATION
- 2011-08-28 10:55:49下载
- 积分：1
