New preprint in SSRN: Deciphering the Transformation of Sounds into Meaning: Insights from Disentangling Intermediate Representations in Sound-to-Event DNNs.

2024-10-21

In this new paper,we examine the nature of sound representations in intermediate layers of convolutional DNNs  by means of in silico experiments involving a new sound data set of material and actions. Furthermore, by means of a new methodology based on invertible neural networks, we show that there is a causal relationship between these internal representations and the semantic model output.

Deciphering the Transformation of Sounds into Meaning: Insights from Disentangling Intermediate Representations in Sound-to-Event DNNs.  Tim Dick, Alexia Briassouli, Enrique Hortal Quesada and Elia Formisano (2024) Available at SSRN: https://ssrn.com/abstract=4979651 or http://dx.doi.org/10.2139/ssrn.4979651.