Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.10153 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910207861325824 |
|---|---|
| author | Kawa, Piotr Howil, Kornel Borycki, Piotr Adamczyk, Miłosz Spurek, Przemysław Syga, Piotr |
| author_facet | Kawa, Piotr Howil, Kornel Borycki, Piotr Adamczyk, Miłosz Spurek, Przemysław Syga, Piotr |
| contents | Explainable AI (XAI) has achieved remarkable success in image classification, yet the audio domain lacks equally mature solutions. Current methods apply vision-based attribution techniques to spectrograms, overlooking fundamental differences between visual and acoustic signals. While prototype reasoning is promising, acoustic similarity remains multidimensional. We introduce APEX (Audio Prototype EXplanations), a post-hoc framework for interpreting pre-trained audio classifiers. Crucially, APEX requires no fine-tuning of the original backbone and strictly preserves output invariance. APEX disentangles explanations into four perspectives: Square-based prototypes to localize transient events, Time-based for temporal patterns, Frequency-based highlighting spectral bands, and Time-Frequency-based integrating both. This yields intuitive, example-based explanations that respect acoustic properties, providing greater semantic clarity than standard gradient-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10153 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | APEX: Audio Prototype EXplanations for Classification Tasks Kawa, Piotr Howil, Kornel Borycki, Piotr Adamczyk, Miłosz Spurek, Przemysław Syga, Piotr Sound Machine Learning Explainable AI (XAI) has achieved remarkable success in image classification, yet the audio domain lacks equally mature solutions. Current methods apply vision-based attribution techniques to spectrograms, overlooking fundamental differences between visual and acoustic signals. While prototype reasoning is promising, acoustic similarity remains multidimensional. We introduce APEX (Audio Prototype EXplanations), a post-hoc framework for interpreting pre-trained audio classifiers. Crucially, APEX requires no fine-tuning of the original backbone and strictly preserves output invariance. APEX disentangles explanations into four perspectives: Square-based prototypes to localize transient events, Time-based for temporal patterns, Frequency-based highlighting spectral bands, and Time-Frequency-based integrating both. This yields intuitive, example-based explanations that respect acoustic properties, providing greater semantic clarity than standard gradient-based methods. |
| title | APEX: Audio Prototype EXplanations for Classification Tasks |
| topic | Sound Machine Learning |
| url | https://arxiv.org/abs/2605.10153 |