Project CETI - An Initiative to Listen to and Decode the Communication of Sperm Whales

This session was presented in the conference: Human-Animal Relations - Challenges and Opportunities in Changing Realities, which took place virtually on June 1-3, 2021.

Shane Gero, Carleton University; Founder of The Dominica Sperm Whale Project and
Michael Bronstein, Imperial College London; Twitter, UK; Project CETI, Dominica

The past decade has witnessed a groundbreaking rise of machine learning for human
language analysis, with current methods capable of automatically accurately recovering
various aspects of syntax and semantics — including sentence structure and grounded word
meaning — from large data collections. Recent research showed the promise of such tools for
analyzing acoustic communication in nonhuman species. We posit that machine learning will
be the cornerstone of future collection, processing, and analysis of multimodal streams of
data in animal communication studies, including bioacoustic, behavioral, biological, and
environmental data. Cetaceans are unique non-human model species as they possess
sophisticated acoustic communications, but utilize a very different encoding system that
evolved in an aquatic rather than terrestrial medium. Sperm whales, in particular, with their
highly-developed neuroanatomical features, cognitive abilities, social structures, and discrete
click-based encoding make for an excellent starting point for advanced machine learning
tools that can be applied to other animals in the future. We present a roadmap toward this
goal based on currently existing technology and outline the key elements required for the
collection and processing of massive bioacoustic data of sperm whales, detecting their basic
communication units and language-like higher-level structures, and validating these models
through interactive playback experiments. The technological capabilities developed by such
an undertaking are likely to yield cross-applications and advancements in broader
communities investigating non-human communication and animal behavioral research.

For more information (including the full program, main sessions and contact information), please visit our website:

[sianmeeuwsen]

This is so exciting - whale communication has been a passion of mine since childhood so I am following this amazing initiative in absolute glee.

[timmcdraw]

I was listening to this while working in my paintings studio and I just got an idea - I don’t know if it’s stupid, or if they will talk about it later in the show, or if it’s even worth anything… but I was thinking that since they see in the depth using echo location, with their clicks, and also they click to hold conversations with their pod, what if it’s not a language in the way we think of it, with grammar etc, but what if they’re painting to one another! Literally painting pictures, in 3D, using echo location memories or imaginings, for example reporting on hunts by clicking the “visuals” of their echo location as they were during the hunt?

[hanskraut]

Good Job on using the right tools. (A thing to put on the wales by wacuume or smth like that that records stuff might be a low cost thing than to have to get microphones by chasing. Altho drones are also a possiblility eather droping microphones or stationary ones.

In the end furthering deep lerning/ AI /machine lerning will increase the economy and therefore animal rights and budgets for animal habitat protection and research will increase. That is what happened when humans got way richer. As there problems improbed they had more patientce for such things.

Good Job. Also maybe it might be lower cost to just have some dog or rat (since rat i heared are quite social, or some animal that somehow communicates a lot (probably more in group living animals) in the lab than chasing spermwales. BUT who knows. Definitly awesome that you use computers and modern human tools. Nice