mlsanityData to 14 Oct 2026

Listenable Maps for Zero-Shot Audio Classifiers

arXiv 2405.17615 ↗First posted 27 May 2024cs.SD cs.LG eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthiness of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in the Zero-Shot context), which, to the best of our knowledge, is the first decoder-based post-hoc interpretation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that maximizes the faithfulness to the original similarity between a given text-and-audio pair. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 50 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

33 of 50 references.

References · 33

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2018Sanity Checks for Saliency Mapscited by 1,156
  7. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  8. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  9. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  10. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  11. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  12. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
21 more
  1. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 574
  2. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  3. 2019Clotho: An Audio Captioning Datasetcited by 358
  4. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 342
  5. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  6. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 188
  7. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  8. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  9. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 129
  10. 2018AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmarkcited by 72
  11. 2021What is the ground truth? Reliability of multi-annotator data for audio taggingcited by 29
  12. 2023Opti-CAM: Optimizing saliency maps for interpretabilitycited by 25
  13. 2022Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMFcited by 23
  14. 2020audioLIME: Listenable Explanations Using Source Separationcited by 22
  15. 2020Reliable Local Explanations for Machine Listeningcited by 18
  16. 2024Listenable Maps for Audio Classifierscited by 13
  17. 2021Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualitiescited by 9
  18. 2024Focal Modulation Networks for Interpretable Sound Classificationcited by 8
  19. 2018Classifier-agnostic saliency map extractioncited by 7
  20. 2023Posthoc Interpretation via Quantizationcited by 7
  21. 2024Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audiocited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024LMAC-TD: Producing Time Domain Explanations for Audio Classifierscited by 4
  2. 2024Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speechcited by 4
  3. 2026AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detectioncited by 0