| 音频DCT系数分布函数的建模 |
| |
| 作者姓名： | 王翠平 郭立 王昱洁 陈运必 |
| |
| 作者单位： | 1. 中国科学技术大学电子科学与技术系, 合肥 230027;
2. 青岛大学自动化工程学院电子学系, 山东青岛 266071 |
| |
| 基金项目： | 国家自然科学基金(60772032)资助 |
| |
| 摘 要： | 针对DCT系数的非高斯性以及广义高斯分布和α稳定分布在音频DCT系数建模上的局限性,提出了一种混合模型.该模型由广义高斯分布和α稳定分布线性加权而成,其加权系数由遗传算法产生.模型的准确性由衡量2个概率分布之间差异的物理量Kullback-Leibler Divergence(KL散度)测量.实验结果表明,提出的混合模型接近于真实分布,并可用于音频检索和隐写分析.
|
| 关 键 词： | 离散余弦变换 混合模型 广义高斯分布 α稳定分布 遗传算法 KL散度 |
| 收稿时间： | 2010-09-08 |
| 修稿时间： | 2010-11-15 |
Distributions of audio DCT coefficients |
| |
| Authors: | WANG Cui-Ping GUO Li WANG Yu-Jie CHEN Yun-Bi |
| |
| Institution: | 1. Department of Electronic Science and Technology, USTC, Hefei 230027, China;
2. Department of Electronics, College of Automation Engineering, Qingdao University, Qingdao 266071, Shandong, China |
| |
| Abstract: | Considering the non-gaussian property of discrete cosine transform(DCT) coefficients of audio and the limitation of modeling the DCT coefficient distribution with a single distribution such as generalized gaussian distribution(GGD) or alpha stable distribution, we propose a mixed model. This mixed model is a linearly weighted average of GGD and alpha stable distribution, while the weight values are obtained using a genetic algorithm. The model accuracy is measured with the Kullback-Leibler Divergence, a metric for evaluating the difference between two probability distributions. Experiment results show that the mixed model is close to the true distribution of DCT coefficients and is of practical use in the field of audio retrieval and steganalysis. |
| |
| Keywords: | DCT mixture model generalized Gaussian distribution alpha stable distribution genetic algorithm KL divergence |
|
| 点击此处可从《》浏览原始摘要信息 |
| 点击此处可从《》下载免费的PDF全文 |
|
