| Audio Segmentation via the Similarity Measure of Audio Feature Vectors |
| |
| 作者姓名： | CHEN Gang TAN Hui CHEN Xin-meng |
| |
| 作者单位： | [1]School of Computer, Wuhan University, Wuhan 430072, Hubei, China |
| |
| 基金项目： | Supported by the National Natural Science Foundation of China （10371033） |
| |
| 摘 要： | A formula to compute the similarity between two audio feature vectors is proposed, which can map arbitrary pair of vectors with equivalent dimension to 0,1）. To fulfill the task of audio segmentation, a self-similarity matrix is computed to reveal the inner structure of an audio clip to be segmented. As the final result must be consistent with the subjective evaluation and be adaptive to some special applications, a set of weights is adopted, which can be modified through relevance feedback techniques. Experiments show that satisfactory result can be achieved via the algorithm proposed in this paper.
|
| 关 键 词： | 音频分割 测量方法 自模仿矩阵 反馈系统 |
| 文章编号： | 1007-1202（2005）05-0833-05 |
| 收稿时间： | 2004-10-20 |
Audio segmentation via the similarity measure of audio feature vectors |
| |
| CHEN Gang TAN Hui CHEN Xin-meng.Audio Segmentation via the Similarity Measure of Audio Feature Vectors[J].Wuhan University Journal of Natural Sciences,2005,10(5):833-837. |
| |
| Authors: | Chen Gang Tan Hui Chen Xin-meng |
| |
| Institution: | (1) School of Computer, Wuhan University, 430072 Wuhan, Hubei, China |
| |
| Abstract: | A formula to compute the similarity between two audio feature vectors is proposed, which can map arbitrary pair of vectors with equivalent dimension to \0,1). To fulfill the task of audio segmentation, a self-similarity matrix is computed to reveal the inner structure of an audio clip to be segmented. As the final result must be consistent with the subjective evaluation and be adaptive to some special applications, a set of weights is adopted, which can be modified through relevance feedback techniques. Experiments show that satisfactory result can be achieved via the algorithm proposed in this paper. |
| |
| Keywords: | audio segmentation abrupt change detection overall error similarity measure self-similarity matrix relevance feedback |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
