Skip to main content
Advertisement

< Back to Article

The detection of algebraic auditory structures emerges with self-supervised learning

Fig 3

Effect of the pretraining dataset on the emergence of structure detection.

We plot as a function of the amount of pretraining the ability of models trained on speech (A), environmental sounds (B) or music (C). Modeled studies: [8,14,21,23].

Fig 3

doi: https://doi.org/10.1371/journal.pcbi.1013271.g003