REVIEW 2 cited by
audioLIME: Listenable Explanations Using Source Separation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpretable Model-agnostic Explanations (LIME) extended by a musical definition of locality. The perturbations used in LIME are created by switching on/off components extracted by source separation which makes our explanations listenable. We validate audioLIME on two different music tagging systems and show that it produces sensible explanations in situations where a competing method cannot.
Forward citations
Cited by 2 Pith papers
-
Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI
ConvAD replaces input occlusion in post-hoc explanation with neuron deactivation in a CNN forward pass, yielding more robust causal explanations with no retraining.
-
Deep Learning-Based Facial Expression Recognition for the Elderly: A Systematic Review
After reviewing 31 studies, the paper reports that deep learning facial expression recognition for elderly people is dominated by CNNs and lightweight models, while age-balanced datasets, privacy safeguards, and expla...
Discussion (0). Continue with ORCID to comment.