中文摘要：

近年来,互联网上出现了海量音乐信息,手工选取某首歌曲很多时候已经变得不可能.这直接促使产生了能够进行音乐自动识别的数字音频指纹技术,并成为研究界和工业界一个非常活跃的研究开发领域.数字音频指纹是指可以代表一段音乐重要声学特征的基于内容的紧致数字签名,其主要目的是建立一种有效机制来比较两个音频文件的感知听觉质量,可用在音频识别、内容完整性校验等应用中.本文介绍音频指纹技术的产生背景、基本概念及性质、典型应用场合及模型,澄清了音频指纹这一术语在音频识别和音频水印中的区别,综述了现有的绝大多数典型音频指纹算法,最后讨论了存在的问题并提出了可能的解决方案.

英文摘要：

Recently, numerous music on the Internet has given rise to the technique called ＂Audio Fingerprinting＂, which is now very active in the research community and industry. Digital audio fingerprint is a robust content-based compact signature that summarizes an audio recording, it is typically used for automatic music identification and audio verification. This paper gives a vision on the background, concepts and properties of audio fingerprinting, clarifies the differences between the same term ＂audio fingerprint＂ simultaneously used in audio identification and audio watermarking, enumerates several representative application scenarios, and summarizes most state-of-the-art audio fingerprinting algorithms. Several barriers that hinder further advance of this technique and possible solutions are also discussed and concluded.