使用m文件产生加噪声的射频信号，通过滤波得到中频信号和基带信号，然后对其取倒谱。经过门特卡罗仿真，采用统计方式，得到各点的概率分布律，然后计算结果的香农熵和互雷尼信息熵。
M files generated using the RF signal plus noise, obtained by filtering the IF signal and baseband signal, and then take its cepstrum. After the door Monte Carlo simulation, using statistical methods to obtain the probability distribution law of each point, and then calculate the result of Shannon entropy and mutual information entropy Rainey. (2013-10-09, matlab, 24KB, 下载13次)
提出了一种支持矢量机的汉语声调识别新方法。论文首先在基频和对数能量的基础上，建立了一个适合于支
持矢量机分类的等维声调特征。然后对支持矢量机的多分类策略和不同核函数对声调识别的影响进行了实验研究。
与BP神经网络相比，支持矢量机具有更高的识别率和更强的推广能力。
This paper presents a novel support vector machine based Chinese tone recognition method．A
new tone recognition feature is first ex血acted using the fundamental frequency(FO)and logarithmic
energy．And how to select the method of SVM multi-class classification and kernel function is also discussed
by experiments．Compared with BP neural network，SVM has higher recognition rates and more strong
generalization． (2012-10-12, matlab, 461KB, 下载16次)
通过核 K- 均值聚类的方法对语音帧进行聚类 , 由于聚类的中心能够很好地代表类内的特征, 用中心样本帧取代该类, 减少了核矩阵的维数, 然后再采用稀疏 KPCA方法对核矩阵进行特征提取。
Through the nuclear K-means clustering method for clustering of speech frames, the cluster center can be a good representative of the class characteristics of the sample frame to replace the class with the center, reducing the dimension of the nuclear matrix, and then use Sparse KPCA method for feature extraction of the nuclear matrix. (2011-11-17, matlab, 181KB, 下载71次)
西奥多里蒂斯著，李晶皎译
本书系统阐述了模式识别的原理与方法，并在此基础上介绍了模式识别的应用。全书分为：基础部分和应用部分：基础部分主要包括统计模式识别、模糊模式识别、神经网络模式识别等内容；应用部分有车牌识别和语音识别。
This paper discussed the principles and methods of pattern recognition, and based on this, the application of pattern recognition. Encyclopedia is divided into: basic part and application part: basic parts mainly include statistical pattern recognition, the fuzzy pattern recognition, neural network pattern recognition content Application part have license plate identification and voice recognition. (2011-09-13, matlab, 8360KB, 下载24次)
为了提高语音分离算法的收敛速度以及分离性能，提出把拉普拉斯正态混合分布概率密度函数作为语音信号概率密度函数的估计，得到一个更加适合语音信号分离的激活函数，基于此函数提出一种快速语音分离算法.
In order to improve speech separation algorithm convergence speed and separation performance, raise the normal mixture distribution Laplace probability density function as the voice signal probability density function estimation, be a more suitable for speech signal separation of activation function, this function is proposed based on kind of fast speech separation algorithm. (2010-06-10, matlab, 1KB, 下载54次)
为虚拟管家系统设计一个麦克风阵列接口，该接口用于接收语音信号作为命令，由麦克风接收识别后用来控制虚拟管家，进而控制各种家用电器工作。当用户移动时，该接口可以跟踪定位用户（此应用中只需知道用户方向角，也是一维定位），即可随时响应用户的控制命令
Housekeeper system for the design of a virtual microphone array interface, the interface for receiving voice signal as a command, from the microphone after receiving recognition used to control a virtual butler, thereby control the various kinds of electrical work. When the user moves, the interface positioning to track users (this application only need to know the user direction angle, but also one-dimensional positioning), at any time in response to the user' s control commands (2009-03-06, matlab, 1618KB, 下载23次)