Shane Geroa cetacean biologist at Carleton University in Canada, has studied communication between whales for more than 20 years. According to his research, sperm whales have specific sounds that identify their families and use “dialects” depending on their location. Although various species like dolphins, elephants and birds also use sounds with patterns to communicate, understanding these subtleties is a daunting task for humans. This is precisely where artificial intelligence comes into play, as it is able to distinguish these small variations.
According to a recent article from Natureover the past year, several AI-backed research has found that African elephants and common marmosets assign names to their companions. Additionally, several machine learning tools map crow calls, allowing exploration of animal self-awareness. Despite these advances, translating animal sounds remains a major challenge. “It’s a big assumption to think that we can apply this technology to other species and get translations,” explains David Gruberfounder of Projet CETI (Cetacean Translation Initiative)focused on the acoustic communication of sperm whales.
Gero, with funding from the CETI Project, collected data from more than 30 sperm whale families in the Caribbean. These whales, which forage at depths of up to 2,000 meters, use audible clicks called “codas” to communicate. Each group, led by females, has unique diets, behaviors and dialects. Differences in the rhythm of codas create cultural boundaries between clans, according to Gero. Thanks to AI, the analysis of these sounds has become more efficientmaking it possible to identify complete conversations and subtle variations such as “rubatos” and “ornaments” (terms borrowed from music).
In parallel, Mickey Pardobehavioral ecologist, demonstrated that African Elephants Make Unique Sounds That Could Be Names. Using AI models, he found that these sounds have an accuracy of 27.5% in identifying individuals. In similar experiments, the neuroscientist David Omer found that marmosets of the same family share acoustic characteristics by “naming” each other.
The goal of these studies is not only to understand these languages, but also to expand animal vocabularieslike location terms in elephants. AI tools not only decipher patterns, but also shed light on the rich world of animal communication, with great potential for promote the conservation of species.
