Search: onr:"swepub:oai:DiVA.org:kth-291301" >
Reliable Local Expl...
Reliable Local Explanations for Machine Listening
-
Mishra, S. (author)
-
Benetos, E. (author)
-
- Sturm, Bob, 1975- (author)
- KTH,Tal, musik och hörsel, TMH
-
show more...
-
Dixon, S. (author)
-
show less...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers Inc. 2020
- 2020
- English.
-
In: 2020 International Joint Conference on Neural Networks (IJCNN). - : Institute of Electrical and Electronics Engineers Inc..
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- One way to analyse the behaviour of machine learning models is through local explanations that highlight input features that maximally influence model predictions. Sensitivity analysis, which involves analysing the effect of input perturbations on model predictions, is one of the methods to generate local explanations. Meaningful input perturbations are essential for generating reliable explanations, but there exists limited work on what such perturbations are and how to perform them. This work investigates these questions in the context of machine listening models that analyse audio. Specifically, we use a state-of-the-art deep singing voice detection (SVD) model to analyse whether explanations from SoundLIME (a local explanation method) are sensitive to how the method perturbs model inputs. The results demonstrate that SoundLIME explanations are sensitive to the content in the occluded input regions. We further propose and demonstrate a novel method for quantitatively identifying suitable content type(s) for reliably occluding inputs of machine listening models. The results for the SVD model suggest that the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- Explainable AI
- Interpretable Machine Learning
- Machine Listening
- Sensitivity analysis
- Influence model
- Input features
- Input perturbation
- Machine learning models
- Model prediction
- Singing voice detection
- State of the art
- Neural networks
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database