A team of researchers is working on finding ways to use machine learning to translate animal “languages” into something humans can understand. They aim to apply it to the whole animal kingdom which is a highly ambitious plan.
The Guardian reports that a California-based nonprofit Earth Species Project (ESP), which was founded in 2017 with the help of Silicon Valley investors like LinkedIn cofounder Reid Hoffman, plans to first decode animal communication with the help of machine learning, and then make its findings available to all.
ESP co-founder and president Aza Raskin says that the group, which published its first paper in December 2021, doesn’t discriminate and is looking to help humans communicate with, or at least understand, as many species as possible.
“We’re species agnostic,” Raskin told The Guardian, adding that the translation algorithms the ESP is developing are designed to “work across all of biology, from worms to whales.”
In the interview, Raskin linked the group’s ambitions to “going to the Moon,” especially given that, like humans, animals also have various forms of non-verbal communication, like bees doing a special “wiggle dance” to indicate to each other that they should land on a specific flower.
The whole process requires a great deal of patience and persistence as it is teeming with impracticalities (supposed). Still, the project has made at least some progress, including an experimental algorithm that can purportedly detect which individual in a noisy group of animals is “speaking.”
A second algorithm reportedly can generate mimicked animal calls to “talk” directly to them.
“It is having the AI speak the language,” Raskin told The Guardian, “even though we don’t know what it means yet.”
While there are certainly exciting implications to this kind of research, particularly when it comes to conservation and convincing skeptics that animals are worth saving, Raskin admits that AI likely won’t be the only answer to saving them.
“These are the tools that let us take off the human glasses,” he concluded, “and understand entire communication systems.”