基于音频指纹特征的高效音乐检索方法  

An Efficient Music Retrieval Method Based on Audio Fingerprint Feature

作　　者：赵修文 刘伍颖 李甫玉 黄心怡 ZHAO Xiuwen;LIU Wuying;LI Fuyu;HUANG Xinyi(General Brigade of Xinjiang PAP,Urumqi 830063,China;Laboratory of Language Engineering and Computing;School of Cyber Security,Guangdong University of Foreign Studies,Guangzhou 510420,China)

机构地区：[1]武警新疆总队,乌鲁木齐830063 [2]广东外语外贸大学语言工程与计算实验室,广州510420 [3]广东外语外贸大学网络空间安全学院,广州510420

出　　处：《武警工程大学学报》2018年第4期27-32,共6页Journal of Engineering University of the Chinese People＇s Armed Police Force

基　　金：国家语委重点项目“面向21世纪海上丝绸之路的稀缺语言资源建设及应用研究”（ZD1135-26）

摘　　要：随着移动智能终端的普及，如何根据输入音频内容进行音乐检索成为了极具科学意义和实用价值的研究热点问题。结合探索基于音频指纹特征的高效音乐检索方法，设计了结构化良好的数据结构、音频特征提取和匹配算法，并在安卓操作系统上实现了音乐识别，实验结果证明了该数据结构和算法的有效性和高效性。With the popularity of mobile intelligent terminals, audio content-based music retrieval has gradually become the focus issue of great scientific significance and practical value. A well-tuned data sturcture, an audio feature extraction method and an improved matching algorithm are designed based on audio content-based musical retvieval according to the audio fingerprint （AFP） feature. Experimental results verify the effectiveness of the proposed data structure and the efficiency of the improved algorithm.

关 键 词：音乐检索 音频指纹 听音识曲 移动智能终端 安卓操作系统 

分 类 号：TN912.3[电子电信—通信与信息系统]