# Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF

arXiv: https://arxiv.org/abs/2202.11479 · HTML: https://mlsanity.com/paper/2202.11479/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Generating Visual Explanations](https://mlsanity.com/paper/1603.08507/) (2016)
- [Learning to Separate Object Sounds by Watching Unlabeled Video](https://mlsanity.com/paper/1804.01665/) (2018)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images](https://mlsanity.com/paper/1512.02017/) (2015)
- [Explaining a black-box using Deep Variational Information Bottleneck Approach](https://mlsanity.com/paper/1902.06918/) (2019)
- [Toward Interpretable Music Tagging with Self-Attention](https://mlsanity.com/paper/1906.04972/) (2019)
- [A Framework to Learn with Interpretation](https://mlsanity.com/paper/2010.09345/) (2020)
- [audioLIME: Listenable Explanations Using Source Separation](https://mlsanity.com/paper/2008.00582/) (2020)
- [Knowledge Transfer from Weakly Labeled Audio using Convolutional Neural Network for Sound Events and Scenes](https://mlsanity.com/paper/1711.01369/) (2017)
- [Reliable Local Explanations for Machine Listening](https://mlsanity.com/paper/2005.07788/) (2020)
- [SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context](https://mlsanity.com/paper/2009.05188/) (2020)
- [Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities](https://mlsanity.com/paper/2106.07787/) (2021)
- [Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding](https://mlsanity.com/paper/1709.07124/) (2017)
- [Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision](https://mlsanity.com/paper/1811.04000/) (2018)
- [CRNNs for Urban Sound Tagging with spatiotemporal context](https://mlsanity.com/paper/2008.10413/) (2020)

## Built on by (most cited first, 23 of 23)

- [A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation](https://mlsanity.com/paper/2306.07304/) (2023)
- [Open-Source Conversational AI with SpeechBrain 1.0](https://mlsanity.com/paper/2407.00463/) (2024)
- [Listenable Maps for Audio Classifiers](https://mlsanity.com/paper/2403.13086/) (2024)
- [Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier](https://mlsanity.com/paper/2208.12485/) (2022)
- [Focal Modulation Networks for Interpretable Sound Classification](https://mlsanity.com/paper/2402.02754/) (2024)
- [Posthoc Interpretation via Quantization](https://mlsanity.com/paper/2303.12659/) (2023)
- [Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization](https://mlsanity.com/paper/2305.07132/) (2023)
- [Transformation of audio embeddings into interpretable, concept-based representations](https://mlsanity.com/paper/2504.14076/) (2025)
- [LMAC-TD: Producing Time Domain Explanations for Audio Classifiers](https://mlsanity.com/paper/2409.08655/) (2024)
- [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)
- [Restyling Unsupervised Concept Based Interpretable Networks with Generative Models](https://mlsanity.com/paper/2407.01331/) (2024)
- [Audio Explanation Synthesis with Generative Foundation Models](https://mlsanity.com/paper/2410.07530/) (2024)
- [Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer](https://mlsanity.com/paper/2505.22199/) (2025)
- [TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization](https://mlsanity.com/paper/2412.01488/) (2024)
- [From Vision to Sound: Advancing Audio Anomaly Detection with Vision-Based Algorithms](https://mlsanity.com/paper/2502.18328/) (2025)
- [From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's Disease](https://mlsanity.com/paper/2507.16836/) (2025)
- [Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations](https://mlsanity.com/paper/2504.08919/) (2025)
- [TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models](https://mlsanity.com/paper/2601.09776/) (2026)
- [AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detection](https://mlsanity.com/paper/2603.18247/) (2026)
- [Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition](https://mlsanity.com/paper/2609.33486/) (2026)
- [Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations](https://mlsanity.com/paper/2609.34030/) (2026)

## Abstract (arXiv)

This paper tackles post-hoc interpretability for audio processing networks. Our goal is to interpret decisions of a network in terms of high-level audio objects that are also listenable for the end-user. To this end, we propose a novel interpreter design that incorporates non-negative matrix factorization (NMF). In particular, a carefully regularized interpreter module is trained to take hidden layer representations of the targeted network as input and produce time activations of pre-learnt NMF components as intermediate outputs. Our methodology allows us to generate intuitive audio-based interpretations that explicitly enhance parts of the input signal most relevant for a network's decision. We demonstrate our method's applicability on popular benchmarks, including a real-world multi-label classification task.