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

arXiv: https://arxiv.org/abs/2208.12485 · HTML: https://mlsanity.com/paper/2208.12485/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 39 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset](https://mlsanity.com/paper/1810.12247/) (2018)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Activation Functions: Comparison of trends in Practice and Research for Deep Learning](https://mlsanity.com/paper/1811.03378/) (2018)
- [Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors](https://mlsanity.com/paper/2006.15417/) (2020)
- [TensorLy: Tensor Learning in Python](https://mlsanity.com/paper/1610.09555/) (2016)
- [Convolutional Feature Masking for Joint Object and Stuff Segmentation](https://mlsanity.com/paper/1412.1283/) (2014)
- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)
- [audioLIME: Listenable Explanations Using Source Separation](https://mlsanity.com/paper/2008.00582/) (2020)
- [Prototype Learning for Interpretable Respiratory Sound Analysis](https://mlsanity.com/paper/2110.03536/) (2021)
- [Reliable Local Explanations for Machine Listening](https://mlsanity.com/paper/2005.07788/) (2020)
- [Robust Semantic Interpretability: Revisiting Concept Activation Vectors](https://mlsanity.com/paper/2104.02768/) (2021)
- [Towards Explainable Music Emotion Recognition: The Route via Mid-level Features](https://mlsanity.com/paper/1907.03572/) (2019)
- [Large-Scale MIDI-based Composer Classification](https://mlsanity.com/paper/2010.14805/) (2020)
- [Deep Composer Classification Using Symbolic Representation](https://mlsanity.com/paper/2010.00823/) (2020)
- [Interpretability for Multimodal Emotion Recognition using Concept Activation Vectors](https://mlsanity.com/paper/2202.01072/) (2022)
- [Towards Musically Meaningful Explanations Using Source Separation](https://mlsanity.com/paper/2009.02051/) (2020)
- [On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples](https://mlsanity.com/paper/2107.09045/) (2021)

## Built on by (most cited first, 12 of 12)

- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Detecting music deepfakes is easy but actually hard](https://mlsanity.com/paper/2405.04181/) (2024)
- [Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization](https://mlsanity.com/paper/2305.07132/) (2023)
- [MusicLIME: Explainable Multimodal Music Understanding](https://mlsanity.com/paper/2409.10496/) (2024)
- [Predicting Music Hierarchies with a Graph-Based Neural Decoder](https://mlsanity.com/paper/2306.16955/) (2023)
- [Prevailing Research Areas for Music AI in the Era of Foundation Models](https://mlsanity.com/paper/2409.09378/) (2024)
- [PBSCR: The Piano Bootleg Score Composer Recognition Dataset](https://mlsanity.com/paper/2401.16803/) (2024)
- [Semantic-Aware Interpretable Multimodal Music Auto-Tagging](https://mlsanity.com/paper/2505.17233/) (2025)
- [Style-based Composer Identification and Attribution of Symbolic Music Scores: a Systematic Survey](https://mlsanity.com/paper/2506.12440/) (2025)
- [MUSE-Explainer: Counterfactual Explanations for Symbolic Music Graph Classification Models](https://mlsanity.com/paper/2509.26521/) (2025)
- [ConceptCaps: a Distilled Concept Dataset for Interpretability in Music Models](https://mlsanity.com/paper/2601.14157/) (2026)
- [Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations](https://mlsanity.com/paper/2609.34030/) (2026)

## Abstract (arXiv)

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.