Incorporating Total Variation Regularization in the design of an intelligent Query by Humming system

TL;DR

This paper enhances a Query-By-Humming system by integrating Total Variation Regularization for denoising queries, improving melody extraction accuracy and overall system performance using deep learning classification.

Contribution

It introduces the use of Total Variation Regularization in QBH systems to better handle humming inaccuracies, leading to higher retrieval accuracy.

Findings

Achieved 93% accuracy on MIR-QBSH dataset.

TVR denoising improves melody extraction quality.

System outperforms existing QBH methods.

Abstract

A Query-By-Humming (QBH) system constitutes a particular case of music information retrieval where the input is a user-hummed melody and the output is the original song which contains that melody. A typical QBH system consists of melody extraction and candidate melody retrieval. For melody extraction, accurate note transcription is the key enabling technology. However, current transcription methods are unable to definitively capture the melody and address inaccuracies in user-hummed queries. In this paper, we incorporate Total Variation Regularization (TVR) to denoise queries. This approach accounts for user error in humming without loss of meaningful data and reliably captures the underlying melody. For candidate melody retrieval, we employ a deep learning approach to time series classification using a Fully Convolutional Neural Network. The trained network classifies the incoming query as belonging to one of the target songs. For our experiments, we use Roger Jang's MIR-QBSH dataset which is the standard MIREX dataset. We demonstrate that inclusion of TVR denoised queries in the training set enhances the overall accuracy of the system to 93% which is higher than other state-of-the-art QBH systems.