Onset detection: A new approach to QBH system

TL;DR

This paper introduces a new onset detection method for Query by Humming systems that improves speed, memory efficiency, and accuracy by focusing solely on precise onset detection, supported by statistical analysis.

Contribution

It presents a novel onset detection approach tailored for QBH systems, enhancing performance and providing statistical error measures.

Findings

Better speed and memory efficiency than existing methods

Empirically higher accuracy in onset detection

Provides statistical analysis and error measurement for the detection method

Abstract

Query by Humming (QBH) is a system to provide a user with the song(s) which the user hums to the system. Current QBH method requires the extraction of onset and pitch information in order to track similarity with various versions of different songs. However, we here focus on detecting precise onsets only and use them to build a QBH system which is better than existing methods in terms of speed and memory and empirically in terms of accuracy. We also provide statistical analogy for onset detection functions and provide a measure of error in our algorithm.