# Exploring Local Interpretable Model-Agnostic Explanations for Speech Emotion Recognition with Distribution-Shift

arXiv: https://arxiv.org/abs/2504.05368 · HTML: https://mlsanity.com/paper/2504.05368/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2025.

## Built on by (most cited first, 3 of 3)

- [Introduction to Analytical Software Engineering Design Paradigm](https://mlsanity.com/paper/2505.11979/) (2025)
- [Disentangling Acoustic Cues in Alzheimer's Pathology and Perception: The Roles of Language and Gender](https://mlsanity.com/paper/2607.23977/) (2026)
- [Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition](https://mlsanity.com/paper/2609.33486/) (2026)

## Abstract (arXiv)

We introduce EmoLIME, a version of local interpretable model-agnostic explanations (LIME) for black-box Speech Emotion Recognition (SER) models. To the best of our knowledge, this is the first attempt to apply LIME in SER. EmoLIME generates high-level interpretable explanations and identifies which specific frequency ranges are most influential in determining emotional states. The approach aids in interpreting complex, high-dimensional embeddings such as those generated by end-to-end speech models. We evaluate EmoLIME, qualitatively, quantitatively, and statistically, across three emotional speech datasets, using classifiers trained on both hand-crafted acoustic features and Wav2Vec 2.0 embeddings. We find that EmoLIME exhibits stronger robustness across different models than across datasets with distribution shifts, highlighting its potential for more consistent explanations in SER tasks within a dataset.