Automatic Live Music Song Identification Using Multi-level Deep Sequence Similarity Learning

TL;DR

This paper introduces a novel system for automatic live music song identification using a Siamese CNN model that measures similarity through multi-level deep sequence analysis, achieving high accuracy on a custom dataset.

Contribution

The paper presents a new approach combining similarity learning and deep sequence analysis for live music identification, with a custom dataset and promising results.

Findings

Achieved 87.4% identification accuracy on live music queries.

Proposed a Siamese CNN model utilizing cross-similarity matrices.

Developed a custom dataset for live music song identification.

Abstract

This paper studies the novel problem of automatic live music song identification, where the goal is, given a live recording of a song, to retrieve the corresponding studio version of the song from a music database. We propose a system based on similarity learning and a Siamese convolutional neural network-based model. The model uses cross-similarity matrices of multi-level deep sequences to measure musical similarity between different audio tracks. A manually collected custom live music dataset is used to test the performance of the system with live music. The results of the experiments show that the system is able to identify 87.4% of the given live music queries.