| 基于压缩域特征的音频识别算法 |
| |
| 引用本文： | 蔺国梁. 基于压缩域特征的音频识别算法[J]. 甘肃联合大学学报(自然科学版), 2011, 25(6): 69-73 |
| |
| 作者姓名： | 蔺国梁 |
| |
| 作者单位： | 甘肃联合大学电子信息工程学院,甘肃兰州,730000 |
| |
| 基金项目： | 甘肃省教育厅科研项目(1113-01) |
| |
| 摘 要： | 如何有效地对海量数据尤其是诸如音频之类的多媒体数据进行分析、存储和检索是一个有待解决的问题.由于原始音频数据的非结构化特性,音频检索受到极大的限制.相对于日益成熟的图像与视频检索,音频检索相对滞后.基于内容的音频检索己成为多媒体检索技术的研究热点.本文对基于内容的音频检索的音频分层分割算法展开分析,提出一种基于压缩域特征音频分割域识别算法.经试验结果显示,此算法由于不依赖于具体的应用阈值,使此算法准确率有较大提高.
|
| 关 键 词： | 基于内容的音频检索 特征提取 音频分割 |
Audio Segmentation Recognize Algorithm Based on Compressed Feature |
| |
| LIN Guo-liang. Audio Segmentation Recognize Algorithm Based on Compressed Feature[J]. Journal of Gansu Lianhe University :Natural Sciences, 2011, 25(6): 69-73 |
| |
| Authors: | LIN Guo-liang |
| |
| Affiliation: | LIN Guo-liang(School of Electronic Information Engineering,Gansu Lianhe University,Lanzhou 730000,China) |
| |
| Abstract: | How to analyze,store and retrieve the huge amount of data efficiently,especially for those multimedia data is an imperative problem.Because of the nonstructural character,the development of audio retrieval is restricted hugely.Comparing with image and video retrieval,audio retrieval study is behindhand.Based on content audio retrieval has been the studied hotspot of multimedia retrieval.The paper focuses on the audio segmentation recognize algorithm based on content audio retrieval,and proposed a novel audi... |
| |
| Keywords: | content-based audio retrieval feature extraction audio segmentation |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
