Scientists are using the clicking noises or “codas” of whales to help develop a key to their underwater language. By decoding the marine animals’ various sounds, the team of international experts hopes to create a way for humans to communicate back to them. During their efforts, Project CETI (Cetacean Translation Initiative) will use artificial intelligence. Called natural language processing, the AI will record and interpret roughly 4 billion Sperm whale codas.
From these codas, the team hopes to assign the communication to the appropriate contexts. According to the researchers in Project CETI, the initiative could take up to five years. If they succeed, the next step would be to deploy “chatbots.”
These bots will then attempt to engage in dialog with the whales. The ultimate goal of the project is to unlock the nuances of the aquatic species. And, perhaps the team will also create greater respect for the animal. Michael Bronstein, the lead of machine learning for Project CETI, reflected on this point in an interview with Hakai magazine.
“If we discover that there is an entire civilization basically under our nose — maybe it will result in some shift in the way that we treat our environment,” Bronstein said. “And maybe it will result in more respect for the living world.”
With their initial plan in action, some members of the Project CETI team have likened the language of Sperm whales to a kind of “Morse code.”
However, others aren’t sure it’s quite that simple.
“These [mammals] make a clicking sound at varying frequencies when they are in the company of other whales,” Professor and CETI member Dan Tchernov said. “The question is, is this just a simple code or a true language? Right now, our database is not comprehensive enough to know the answer to this question.”
Researchers Share ‘Greatest Risks’ to Whale Language Initiative
What Morse code or any similar, simplistic language doesn’t allow for is the semantics, grammar and emotion associated with each communication. This is a problem that the Project CETI team may encounter in their attempt to echo the whales’ codas. That’s why, along with AI, the team must also observe the whale’s body language and behavior.
Another threat to the project is the fact that whales may not be as interesting as the researchers believe. Instead, their language could very well be only a few select phrases continuously repeated.
“We understand that one of our greatest risks is that the whales could be incredibly boring,” David Gruber, a marine biologist, said. “But we don’t think this is the case. In my experience as a biologist, whenever I really looked at something closely, there has never been a time when I’ve been underwhelmed by animals.”