DeepAI AI Chat
Log In Sign Up

Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier

by   Francesco Foscarin, et al.
Johannes Kepler University Linz

Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e.g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll. This can be difficult to understand, particularly for musicologists without technical knowledge. To address this issue, we focus on more human-friendly explanations based on high-level musical concepts. Our research targets trained systems (post-hoc explanations) and explores two approaches: a supervised one, where the user can define a musical concept and test if it is relevant to the system; and an unsupervised one, where musical excerpts containing relevant concepts are automatically selected and given to the user for interpretation. We demonstrate both techniques on an existing symbolic composer classification system, showcase their potential, and highlight their intrinsic limitations.


TunesFormer: Forming Tunes with Control Codes

In recent years, deep learning techniques have been applied to music gen...

Deep rank-based transposition-invariant distances on musical sequences

Distances on symbolic musical sequences are needed for a variety of appl...

Learning Unsupervised Hierarchies of Audio Concepts

Music signals are difficult to interpret from their low-level features, ...

Is Disentanglement all you need? Comparing Concept-based Disentanglement Approaches

Concept-based explanations have emerged as a popular way of extracting h...

A Technical Framework for Musical Biofeedback in Stroke Rehabilitation

We here present work a generalized low-level technical framework aimed t...

NetNeg: A Connectionist-Agent Integrated System for Representing Musical Knowledge

The system presented here shows the feasibility of modeling the knowledg...

DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

Explaining deep learning model inferences is a promising venue for scien...