<title>Music identification with MPEG-7</title>

Abstract

Realtime music identification became more and more interesting within the past few years. 1, 2 Possible fields are for example monitoring a radio station in order to create a playlist or scanning network traffic in search of copyright protected material.This paper presents a client-server application to identify an unknown segment of music. The extraction and exchange of descriptive data is done with MPEG-7 only. This paper also explains how to define the similarity between two segments of music and determents its robustness towards perceptional audio coding and filtering. It also introduces an indexing system to reduce the number of segments which have to be compared to the query.

Music Identification System Using MPEG‐7 Audio Signature Descriptors

“…Although low-level descriptors in MPEG-7 audio may also be used to identify music, it is shown that the audio signature descriptors provide better identification performance [18, 19]. Therefore, the audio signature descriptors are adopted in the proposed system.…”

“…In the audio part of the standard [17], a high-level tool is developed for audio identification called audio signature description scheme. The fingerprints used in the scheme are called audio signature descriptors, and they have good identification accuracy [18, 19]. In the following, we interchangeably use descriptors and fingerprints without distinction.…”

A self-similarity approach to repairing large dropouts of streamed music

“…While a Google/AltaVista search engine does not exist for audio, many researchers are discovering ways to automatically locate, index, and browse audio using recent advances in technologies such as speech recognition and machine learning. MPEG-7 as a descriptive tool can greatly enhance this area by adding additional metadata based on the content of the audio as well as standard keyword descriptors [Crysandt 2004].…”

“…Through specific filters on MPEG-7 descriptors a user can specify the type of audio content he/she wants to listen to without any requirement to analyze the audio itself. For example, in one method of similarity analysis [Crysandt 2004] used the mean of the audio power and the mean of the audio spectrum flatness as criteria for a similarity comparison between songs. There are 17 Low-Level Descriptors (LLD) that can appear in a variety of combinations that look at either the temporal or spectral domain of an audio signal.…”