| 足球比赛中的音频信息提取与自动分类 |
| |
| 引用本文： | 于俊清,崔玉强,何云峰.足球比赛中的音频信息提取与自动分类[J].华中科技大学学报(自然科学版),2007,35(10):35-38,45. |
| |
| 作者姓名： | 于俊清 崔玉强 何云峰 |
| |
| 作者单位： | 华中科技大学,计算机科学与技术学院,湖北,武汉,430074 |
| |
| 基金项目： | 湖北省自然科学基金
,
广东省深圳市华为技术有限公司资助项目 |
| |
| 摘 要： | 按照MEPG-7的音频特征规范,设计了帧层次和段层次上的音频特征提取算法.在深入分析足球比赛中各类音频信息的不同特点的基础上,通过有针对性地选取特征,构造特征向量,设计并实现了一种基于决策树的层次化分类算法.该算法可以自动将足球比赛中的音频信息分为噪音、解说员语音、哨音、欢呼声和带背景音的解说员语音等5个类别.实验表明:该算法提取的特征有效,分类效果良好.
|
| 关 键 词： | 特征提取 音频分类 决策树 足球比赛 足球比赛 信息提取 自动 分类效果 game soccer information audio classification extraction 实验 类别 背景音 解说员 噪音 分类算法 层次化 决策树 特征向量 构造 |
| 文章编号： | 1671-4512（2007）10-0035-04 |
| 修稿时间： | 2006-08-24 |
Automatic extraction and classification of audio information in soccer game |
| |
| Yu Junqing,Cui Yuqiang,He Yunfeng.Automatic extraction and classification of audio information in soccer game[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2007,35(10):35-38,45. |
| |
| Authors: | Yu Junqing Cui Yuqiang He Yunfeng |
| |
| Institution: | College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China |
| |
| Abstract: | The extraction algorithm of frame-level and clip-level audio features is designed according to the MPEG-7 audio standard.By deeply analyzing the characteristics of audio information in soccer game,the feature vector is formed and a hierarchical audio classifier is realized based on decision tree.The decision tree audio classifier divides audio information in soccer game into five classes: noise,commentator speech,whistle,cheer and commentator speech with background noise.The experiment results show that the selected features are effective for audio classification,and the classification accuracy is reasonable. |
| |
| Keywords: | feature extraction audio classification decision tree soccer game |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
