# Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities

arXiv: https://arxiv.org/abs/2106.07787 · HTML: https://mlsanity.com/paper/2106.07787/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 14 Jun 2021.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Interpretations are useful: penalizing explanations to align neural networks with prior knowledge](https://mlsanity.com/paper/1909.13584/) (2019)
- [Towards Explainable Artificial Intelligence](https://mlsanity.com/paper/1909.12072/) (2019)
- [Toward Interpretable Music Tagging with Self-Attention](https://mlsanity.com/paper/1906.04972/) (2019)
- [End-to-end learning for music audio tagging at scale](https://mlsanity.com/paper/1711.02520/) (2017)
- [audioLIME: Listenable Explanations Using Source Separation](https://mlsanity.com/paper/2008.00582/) (2020)
- [Reliable Local Explanations for Machine Listening](https://mlsanity.com/paper/2005.07788/) (2020)
- [Towards Explainable Music Emotion Recognition: The Route via Mid-level Features](https://mlsanity.com/paper/1907.03572/) (2019)
- [A data-driven approach to mid-level perceptual musical feature modeling](https://mlsanity.com/paper/1806.04903/) (2018)
- [GAN-based Generation and Automatic Selection of Explanations for Neural Networks](https://mlsanity.com/paper/1904.09533/) (2019)
- [Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs](https://mlsanity.com/paper/1911.05833/) (2019)
- [Towards Musically Meaningful Explanations Using Source Separation](https://mlsanity.com/paper/2009.02051/) (2020)
- [Two-level Explanations in Music Emotion Recognition](https://mlsanity.com/paper/1905.11760/) (2019)
- [Receptive-Field Regularized CNNs for Music Classification and Tagging](https://mlsanity.com/paper/2007.13503/) (2020)
- [Explaining Deep Convolutional Neural Networks on Music Classification](https://mlsanity.com/paper/1607.02444/) (2016)
- [Towards Explaining Expressive Qualities in Piano Recordings: Transfer of Explanatory Features via Acoustic Domain Adaptation](https://mlsanity.com/paper/2102.13479/) (2021)
- [Towards Interpretable Polyphonic Transcription with Invertible Neural Networks](https://mlsanity.com/paper/1909.01622/) (2019)

## Built on by (most cited first, 9 of 9)

- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)
- [Listenable Maps for Audio Classifiers](https://mlsanity.com/paper/2403.13086/) (2024)
- [Perceptual Musical Features for Interpretable Audio Tagging](https://mlsanity.com/paper/2312.11234/) (2023)
- [Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges](https://mlsanity.com/paper/2406.08809/) (2024)
- [Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization](https://mlsanity.com/paper/2305.07132/) (2023)
- [Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech](https://mlsanity.com/paper/2411.08013/) (2024)
- [Listenable Maps for Zero-Shot Audio Classifiers](https://mlsanity.com/paper/2405.17615/) (2024)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)
- [Joint Learning of Emotions in Music and Generalized Sounds](https://mlsanity.com/paper/2408.02009/) (2024)

## Abstract (arXiv)

Music emotion recognition is an important task in MIR (Music Information Retrieval) research. Owing to factors like the subjective nature of the task and the variation of emotional cues between musical genres, there are still significant challenges in developing reliable and generalizable models. One important step towards better models would be to understand what a model is actually learning from the data and how the prediction for a particular input is made. In previous work, we have shown how to derive explanations of model predictions in terms of spectrogram image segments that connect to the high-level emotion prediction via a layer of easily interpretable perceptual features. However, that scheme lacks intuitive musical comprehensibility at the spectrogram level. In the present work, we bridge this gap by merging audioLIME -- a source-separation based explainer -- with mid-level perceptual features, thus forming an intuitive connection chain between the input audio and the output emotion predictions. We demonstrate the usefulness of this method by applying it to debug a biased emotion prediction model.