Reliable Local Explanations for Machine Listening

Mishra, S. (author)

Benetos, E. (author)

Dixon, S. (author)

(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

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.

NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

By the author/editor: Mishra, S.; Benetos, E.; Sturm, Bob, 1975 ...; Dixon, S.

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Science ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.