搜索资源列表
training_gmm
- 训练高斯混合模型的程序，尽管此类代码较多，但本程序经过笔者改写优化后，很大程度上避免了普通方法中局部最优的问题。-Gaussian mixture model training procedures, although the code more, but the procedure after the author rewrite optimization, largely avoiding the ordinary method of optimal local issues.
gmm_creation_mle
- 采用期望最大算法最优化初始高斯混合模型的程序，笔者借用ubm自适应方法，很好的解决了模型不收敛的问题。-expectations largest algorithm using optimization initial Gaussian mixture model procedures, the author borrowed ubm adaptive method, a good model is not the solution convergence problem.
gmm_prob
- 计算高斯混合模型先验概率和后验概率的程序，采用大矩阵运算，大大提高了运行速度。-Gaussian mixture model calculated a priori probability and the probability of post-mortem procedures, using a large matrix computation, greatly improved speed.
DirectxOfMfc
- 一个用MFC和DIRECTX作的3D软件源码，你可以用他作自己的3D模型-a DIRECTX using MFC and 3D software for the source code, you can use him for their own 3D model
Ans_MP3_Decoder_SC_Win32_Algorithm
- 一个基于SystemC的MP3解码器行为模型，可用于MP3解码器的芯片开发-a SystemC-based MP3 decoder behavior model can be used for MP3 decoder chip development
MusicSegmentation_F02
- 音频流提取 音频特征提取 音频分类 可用于说话人模型训练,静音,音乐和背景音的分类-Audio Streaming Audio extraction feature extraction can be used for classification of Audio speaker model training, quiet, Music and background noise classification
ImageFilterBasedP2DHMTModelinWaveletDomain
- 文章提出了一种基于小波域伪二维隐Markov 树（P2DHMT）的图像的滤波新方法。首先建立了小波域的伪 2DHMT 模型，给出了基于EM、Baum-Welch 等算法的模型参数估计方法；
zcpa
- 过零峰值幅度(ZCPA：Zero-cro ingwithPeakAmplitude)特征的语音识别系统，它是基于人耳的听觉模型建立起来的，这是ZCPA的源程序。-Zero-crossing peak amplitudes (ZCPA: Zero-cro ingwithPeakAmplitude) features voice recognition system, which is based on the model of the human ear
Gaussian_mixture_model
- 高斯混合模型[Gaussian mixture model,简称GMM]是单一高斯机率密度函数的延伸,由於GMM 能够平滑地近似任意形状的密度分布,因此近年来常被用在语音与语者辨识,得到不错的效果。 -Gaussian mixture model [Gaussian mixture model, referred to as GMM] are single-Gaussian probability density function of the extension.GMM can approxi
waveplay
- 使用DMA演示一个单一wave文件的示范。 您需要一个巨大的内存模型跑此。 -Demonstration of a single wave file of the model using DMA. You need a great memory model to run this.
cizhu
- 磁珠的阻抗模型 很好的，难得，介绍磁珠的电阻电容电感模型-Impedance model of the magnetic well, rare on the resistance of magnetic inductance capacitance model
TongBu0AC380V_DC750V_15KVA_5kHz_SPWM
- PWM 整流器仿真模型2 有一定代表性-PWM
HMM
- HMM隐马尔科夫模型实现的源代码，c++环境下-HMM Hidden Markov Model to the source code, c++ environment
HUMOVE
- HUMM马尔科夫检测运动目标的文档，HUM为隐马尔科夫模型-HUMM Markov detect moving targets document, HUM for the hidden Markov model
short-wave-channel-simulation-
- 短波信道模型，是基于watterson提出的典型短波信道。-short-wave channel simulation
HMM-model
- 隐马尔科夫模型是语音识别中的重要算法思想，这里在matlab下实现了一个原理性的算法-Hidden markov models is an important algorithm in speech recognition, here under the matlab implements a rational algorithm
ISO-532-1975A
- ISO 532-1975A 响度计算 Stevens模型-ISO 532-1975A loudness calculation Stevens model
inithmm
- 在语音识别算法HMM中，完成对HMM模型进行一定的初始化设置-In speech recognition algorithm HMM, the completion of the HMM model for a certain initialization settings
libogg
- 首先对输入音频PCM信号进行时频分析，决定MDCT的长度，即加窗，然后进行MDCT变换；同时对原始音频信号要进行FFT分析。两种变换的频谱系输入给心理声学模型单元，MDCT系数用于噪声掩蔽计算，H可结果用于音调掩蔽特性计算，共同构造总的掩蔽曲线。然后根据MDCT系数及掩蔽曲线，对频谱系数进行线性预测分析用LPC(Linear Prediction Coefficience，线性预测系数)表示频谱包络，即基底曲线(Floor Curve)；或通过线性分段逼近方式获得基底曲线。从MDCT系数中去掉
rir
- 改程序的功能：基于IMAGE混响模型编写的混响估计程序，条件实在矩形的房子中进行的-Change program features: based on IMAGE reverberation model reverberation estimation program written, just rectangular house