Approaching an unknown communication system by latent space exploration and causal inference
Overview of the networkAbstract
We propose a methodology for discovering meaningful properties in data without ground truth by combining manipulation of the latent variables of generative models to extreme values with causal inference in an approach we call causal disentanglement with extreme values (CDEV). Using it, we investigate what properties the model encodes as meaningful when trained on raw audio of sperm whale (Physeter macrocephalus) communication. The method suggests that the model considers the number of clicks in a sequence, the regularity of their timing, as well as audio properties such as the spectral mean and the acoustic regularity of the sequences as the main components for generating believable and informative data. The first two are consistent with existing hypotheses, while the last two are proposed for the first time. We also argue that our models uncover rules that govern the structure of units in the communication system, suggesting the methodology as a viable strategy for approaching unknown data.
The paper proposes a novel methodology - Causal Disentanglement with Extreme Values (CDEV) - to identify representations learned by a Generative adversarial network (GAN) trained on raw whale communication, proposing – for the first time – specific acoustic attributes that might serve as carriers of meaning.
Followed up in Vowels and Diphthongs in Sperm Whales, which identified concrete patterns in the communication system corresponding to the predicted attributes.
This work has received significant attention, with selected media coverage collected on the Media & Honors page.
