Learning with Music Signals: Technology Meets Education

Abstract

Music information retrieval (MIR) is an exciting and challenging research area that aims to develop techniques and tools for organizing, analyzing, retrieving, and presenting music-related data. Being at the intersection of engineering and humanities, MIR relates to different research disciplines, including signal processing, machine learning, information retrieval, musicology, and the digital humanities. In this tutorial, using music as a tangible and concrete application domain, we will approach the concept of learning from different angles, addressing technological and educational aspects. When talking about learning in an engineering context, one immediately thinks of data-driven techniques such as deep learning (DL), where computer-based systems are trained to extract complex features and hidden relationships from given examples. In this tutorial, we will introduce various music analysis and retrieval tasks, where we start with classical engineering approaches. We then show how such approaches may be rephrased or simulated by DL-based systems, thus indicating new avenues toward building more explainable and hybrid machine-learning systems by learning from the experience of traditional engineering approaches and integrating knowledge from the music domain. Beyond this technical perspective, another aim of this tutorial is to approach the concept of learning from an educational perspective. We argue that music, being an essential part of our lives that everyone feels connected to, yields an intuitive entry point to support education in technical disciplines. In this tutorial, we will show how music may serve as a vehicle to make learning in signal processing and machine learning an interactive pursuit. In this context, we will also introduce a novel collection of educational material for teaching and learning fundamentals of music processing (FMP). This collection, referred to as FMP notebooks (https://www.audiolabs-erlangen.de/FMP) can be used to study both theory and practice, generate educational material for lectures, and provide baseline implementations for many MIR tasks. The tutorial's novelty lies in how it presents a holistic approach to learning using music as a challenging and tangible application domain. In this way, the tutorial serves several purposes: it gives a gentle introduction to MIR while introducing a new software package for teaching and learning music processing, it highlights avenues for developing explainable machine-learning models, and it discusses how recent technology can be applied and communicated in interdisciplinary research and education.