mlsanityData to 7 Oct 2026

LMAC-TD: Producing Time Domain Explanations for Audio Classifiers

arXiv 2409.08655 ↗First posted 13 Sep 2024cs.SD cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Neural networks are typically black-boxes that remain opaque with regards to their decision mechanisms. Several works in the literature have proposed post-hoc explanation methods to alleviate this issue. This paper proposes LMAC-TD, a post-hoc explanation method that trains a decoder to produce explanations directly in the time domain. This methodology builds upon the foundation of L-MAC, Listenable Maps for Audio Classifiers, a method that produces faithful and listenable explanations. We incorporate SepFormer, a popular transformer-based time-domain source separation architecture. We show through a user study that LMAC-TD significantly improves the audio quality of the produced explanations while not sacrificing from faithfulness.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

23 of 31 references.

References · 23

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  9. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  10. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
  11. 2015Deep clustering: Discriminative embeddings for segmentation and separationcited by 211
  12. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
11 more
  1. 2020Attention is All You Need in Speech Separationcited by 184
  2. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 154
  3. 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 154
  4. 2024Open-Source Conversational AI with SpeechBrain 1.0cited by 55
  5. 2020A Framework to Learn with Interpretationcited by 23
  6. 2022Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMFcited by 23
  7. 2020audioLIME: Listenable Explanations Using Source Separationcited by 22
  8. 2024Listenable Maps for Audio Classifierscited by 13
  9. 2023Posthoc Interpretation via Quantizationcited by 7
  10. 2022A Model You Can Hear: Audio Identification with Playable Prototypescited by 6
  11. 2024Listenable Maps for Zero-Shot Audio Classifierscited by 3

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2024Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speechcited by 4
  2. 2025A Data-Driven Diffusion-based Approach for Audio Deepfake Explanationscited by 2
  3. 2026AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detectioncited by 0
  4. 2026Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanationscited by 0