mlsanityData to 7 Oct 2026

audioLIME: Listenable Explanations Using Source Separation

arXiv 2008.00582 ↗First posted 2 Aug 2020cs.SD cs.IR cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpretable Model-agnostic Explanations (LIME) extended by a musical definition of locality. The perturbations used in LIME are created by switching on/off components extracted by source separation which makes our explanations listenable. We validate audioLIME on two different music tagging systems and show that it produces sensible explanations in situations where a competing method cannot.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 2; 2023: 1; 2024: 8; 2025: 5; 2026: 3.

22 papers.

Sort:

  1. 2021What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structurecited by 52
  2. 2022Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMFcited by 23
  3. 2024Listenable Maps for Audio Classifierscited by 13
  4. 2022Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifiercited by 12
  5. 2021Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualitiescited by 9
  6. 2024Focal Modulation Networks for Interpretable Sound Classificationcited by 8
  7. 2025Which LIME should I trust? Concepts, Challenges, and Solutionscited by 7
  8. 2024Explainable Deep Learning Analysis for Raga Identification in Indian Art Musiccited by 6
  9. 2023Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorizationcited by 5
  10. 2025Transformation of audio embeddings into interpretable, concept-based representationscited by 5
  11. 2024LMAC-TD: Producing Time Domain Explanations for Audio Classifierscited by 4
  12. 2024Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speechcited by 4
10 more
  1. 2021On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examplescited by 3
  2. 2024Listenable Maps for Zero-Shot Audio Classifierscited by 3
  3. 2024MusicLIME: Explainable Multimodal Music Understandingcited by 3
  4. 2024One Wave To Explain Them All: A Unifying Perspective On Feature Attributioncited by 3
  5. 2025Investigating Modality Contribution in Audio LLMs for Musiccited by 2
  6. 2025AudioGenX: Explainability on Text-to-Audio Generative Modelscited by 1
  7. 2026I Guess That's Why They Call it the Blues: Causal Analysis for Audio Classifierscited by 1
  8. 2025Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AIcited by 0
  9. 2026Mask-Induced Displacement in Audio XAI via Logit Trajectory Decompositioncited by 0
  10. 2026Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanationscited by 0