A local fingerprinting approach for audio copy detection

TL;DR

This paper introduces a robust audio copy detection system using a novel time-chroma image representation and local fingerprinting that effectively detects copies despite pitch shifts and tempo changes.

Contribution

It presents a new time-chroma image representation and a local fingerprinting algorithm that are invariant to scale changes and outperform existing methods in audio copy detection.

Findings

Outperforms existing methods in robustness to pitch and tempo changes

Accurately estimates pitch shift and tempo change applied to audio

Significantly improves song identification accuracy

Abstract

This study proposes an audio copy detection system that is robust to various attacks. These include the severe pitch shift and tempo change attacks which existing systems fail to detect. First, we propose a novel two dimensional representation for audio signals called the time-chroma image. This image is based on a modification of the concept of chroma in the music literature and is shown to achieve better performance in song identification. Then, we propose a novel fingerprinting algorithm that extracts local fingerprints from the time-chroma image. The proposed local fingerprinting algorithm is invariant to time/frequency scale changes in audio signals. It also outperforms existing methods like SIFT by a great extent. Finally, we introduce a song identification algorithm that uses the proposed fingerprints. The resulting copy detection system is shown to significantly outperform existing methods. Besides being able to detect whether a song (or a part of it) has been copied, the proposed system can accurately estimate the amount of pitch shift and/or tempo change that might have been applied to a song.