Sperm whale alphabet: machine learning brings humans closer to understanding cetacean communication

Scientists claim that thanks to machine learning, they have managed to decipher the sperm whale “alphabet”. This was reported by TechCrunch.

This research was conducted by scientists from the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory (MIT CSAIL) together with Project CETI specialists.

Their work, titled “Contextual and Combinatorial Structure in Sperm Whale Vocalizations,” points to key breakthroughs in human understanding of how cetaceans communicate.

During the study, experts identified certain codes – a series of clicks that perform different linguistic functions.

“We have discovered that coda types are not arbitrary, but rather they form a newly discovered combinatory coding system,” explained Daniela Rus, Director of CSAIL.

Thanks to machine learning, the researchers were able to analyze a dataset of 8719 sperm whale codes collected by researcher Shane Gero.

“Sizable combinatorial vocalization systems are exceedingly rare in nature; however, their use by sperm whales shows that they are not uniquely human, and can arise from dramatically different physiological, ecological, and social pressures,” the study says.

Nevertheless, the specialists still have a lot of work ahead of them – first with sperm whales, and then potentially with other marine mammals such as humpback whales.