Efficient music identification using ORB descriptors of the spectrogram image

Dominic Williams,Akash Pooransingh,Jesse Saitoo

doi:10.1186/s13636-017-0114-4

Dominic Williams, Akash Pooransingh + Show 1 more

Open Access

https://doi.org/10.1186/s13636-017-0114-4

Copy DOI

Abstract

Audio fingerprinting has been an active research field typically used for music identification. Robust audio fingerprinting technology is used to successfully perform content-based audio identification regardless of the audio signal being subjected to various types of distortion. These distortions affect the time-frequency correlation relating to pitch and speed changes. In this paper, experiments are done using the computer vision technique ORB (Oriented FAST and Rotated BRIEF) for robust audio identification. Investigations are conducted for ORB, relating to its advantage of robustness against distortions including speed and pitch changes. The ORB prototype compares the features of the spectrogram image query to a database of spectrogram images of the songs. For the initial experiment, a Brute-Force matcher is used to compare the ORB descriptors. Results show that the ORB prototype performs robustly to real-world distortions with fast, reliable performance against distortions such as speed and pitch which justifies the research done.

Highlights

In recent years, there has been an increase in digital multimedia technology, which made it simpler to share music files
This paper proposes a music identification algorithm that is highly robust to audio signal noise as well as time and frequency domain synchronization changes
The database consisted of the songs being converted to their associated spectrogram image representation

Summary

Introduction

There has been an increase in digital multimedia technology, which made it simpler to share music files. Rublee et al [9] proposed that using image processing techniques for audio identification had an advantage of robustness to distortions such as speed and pitch changes which algorithms such as Shazam was difficult to resist. The audio samples were tested in each case, and the results showed the number of queries that matched for each speed change.

Results

Conclusion