no code implementations • 26 Aug 2022 • Francesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer
Current approaches for explaining deep learning systems applied to musical data provide results in a low-level feature space, e. g., by highlighting potentially relevant time-frequency bins in a spectrogram or time-pitch bins in a piano roll.
1 code implementation • 19 Jul 2021 • Verena Praher, Katharina Prinz, Arthur Flexer, Gerhard Widmer
The basic idea is to identify a small set of human-understandable features of the classified example that are most influential on the classifier's prediction.
2 code implementations • 14 Jun 2021 • Shreyan Chowdhury, Verena Praher, Gerhard Widmer
In previous work, we have shown how to derive explanations of model predictions in terms of spectrogram image segments that connect to the high-level emotion prediction via a layer of easily interpretable perceptual features.