A Hierarchical Deep Learning Approach for Minority Instrument Detection

TL;DR

This paper introduces a hierarchical deep learning method for detecting musical instruments in audio, improving coarse-level recognition by leveraging hierarchical structures and limited annotations.

Contribution

It presents novel strategies for integrating hierarchical classifications into deep learning models for instrument detection in diverse music datasets.

Findings

Enhanced coarse-level instrument detection accuracy

Effective hierarchical model strategies demonstrated on MedleyDB

Bridging detailed and group-level instrument recognition

Abstract

Identifying instrument activities within audio excerpts is vital in music information retrieval, with significant implications for music cataloging and discovery. Prior deep learning endeavors in musical instrument recognition have predominantly emphasized instrument classes with ample data availability. Recent studies have demonstrated the applicability of hierarchical classification in detecting instrument activities in orchestral music, even with limited fine-grained annotations at the instrument level. Based on the Hornbostel-Sachs classification, such a hierarchical classification system is evaluated using the MedleyDB dataset, renowned for its diversity and richness concerning various instruments and music genres. This work presents various strategies to integrate hierarchical structures into models and tests a new class of models for hierarchical music prediction. This study showcases more reliable coarse-level instrument detection by bridging the gap between detailed instrument identification and group-level recognition, paving the way for further advancements in this domain.