mlsanityData to 14 Oct 2026

Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition

arXiv 2305.18011 ↗First posted 29 May 2023cs.CL cs.SD eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

Explainable AI (XAI) techniques have been widely used to help explain and understand the output of deep learning models in fields such as image classification and Natural Language Processing. Interest in using XAI techniques to explain deep learning-based automatic speech recognition (ASR) is emerging. but there is not enough evidence on whether these explanations can be trusted. To address this, we adapt a state-of-the-art XAI technique from the image classification domain, Local Interpretable Model-Agnostic Explanations (LIME), to a model trained for a TIMIT-based phoneme recognition task. This simple task provides a controlled setting for evaluation while also providing expert annotated ground truth to assess the quality of explanations. We find a variant of LIME based on time partitioned audio segments, that we propose in this paper, produces the most reliable explanations, containing the ground truth 96% of the time in its top three audio segments.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

26 of 36 references.

References · 26

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  5. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  6. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  7. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  8. 2016Top-down Neural Attention by Excitation Backpropcited by 321
  9. 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
  10. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  11. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  12. 2016Grad-CAM: Why did you say that?cited by 161
14 more
  1. 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 156
  2. 2020Debugging Tests for Model Explanationscited by 147
  3. 2020Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAIcited by 126
  4. 2020Benchmarking Deep Learning Interpretability in Time Series Predictionscited by 102
  5. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  6. 2021Do Feature Attribution Methods Correctly Attribute Features?cited by 98
  7. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  8. 2019Measuring the Quality of Explanations: The System Causability Scale (SCS). Comparing Human and Machine Explanationscited by 64
  9. 2019DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systemscited by 59
  10. 2019Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithmscited by 32
  11. 2020Assessing the (Un)Trustworthiness of Saliency Maps for Localizing Abnormalities in Medical Imagingcited by 32
  12. 2020What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoorscited by 32
  13. 2019Evaluating Recurrent Neural Network Explanationscited by 29
  14. 2023Explanations for Automatic Speech Recognitioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 4; 2026: 4.

10 papers.

  1. 2023Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Featurescited by 7
  2. 2024SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generationcited by 6
  3. 2025Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translationcited by 5
  4. 2026Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Modelscited by 4
  5. 2025The Unheard Alternative: Contrastive Explanations for Speech-to-Text Modelscited by 3
  6. 2026Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluationcited by 2
  7. 2025On the reliability of feature attribution methods for speech classificationcited by 1
  8. 2025Cross-Attention is Half Explanation in Speech-to-Text Modelscited by 1
  9. 2026Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessmentcited by 0
  10. 2026Disentangling Acoustic Cues in Alzheimer's Pathology and Perception: The Roles of Language and Gendercited by 0