The orangutan's distinctive cries have been decoded with the help of artificial intelligence

While scientists may not yet be able to decipher the ABCs of sperm whales or what elephant gestures mean, there is a lot of activity in studying communication between animals. Now it's the orangutan's turn. Through a combination of traditional recording and analysis with artificial intelligence (AI), scientists have identified three distinct types of beats in the long calls of primates. Their sounds are likely to be more complex, according to A.J A study published May 14 in the journal Life and Environment PeerJ.

Orangutans are great apes found primarily in Southeast Asia. They are the The largest mammal that lives in trees And eat in the first place Insects and flowers. They are also known for their social behavior and complex communication. However, as with many species, understanding the nuances of their vocal repertoire has been a challenge.

[Related: Why do humans talk? Tree-dwelling orangutans might hold the answer.]

“Our research aims to unravel the complexities of orangutans' long calls, which play a crucial role in their communication across vast distances in Indonesia's dense rainforests,” says Wendy Erb, study co-author and a primatologist at Cornell University. He said in a statement. “Over the course of three years, we collected hundreds of long call recordings, revealing an impressive array of vocal diversity,” Erb said.

Their long calls are The loud, booming sounds made by males. They are highly variable depending on the individual and are used to communicate over longer distances between widely separated animals. previous studies Prepare a dictionary of pulse types. Using the same dictionary, Erb and her team sought to determine how many types of pulse they could describe, what features could distinguish them, and how gradual they were.

Using traditionally recorded video and audio sources, Erb and his team used machine learning to carefully analyze the long calls of 13 orangutans. They were looking to determine how many types of pulsation were present in their voices and evaluate their gradation.

“Through a combination of supervised and unsupervised analytical methods, we identified three different types of pulses that are well characterized by both humans and machines,” Erb said. “Although our study represents an important step forward in understanding orangutan communication, there is still much to discover. Orangutans may have a much larger repertoire of vocal types than we have described, highlighting the complexity of their vocal system.”

[Related: Artificial intelligence is helping scientists decode animal languages.]

According to the teamThis work highlights the complexity of sounds in the animal kingdom, pointing out that beats are not just random sounds. It also demonstrates the ability to collaborate across scientific disciplines and combine traditional research methods with advances in artificial intelligence.

“We hope that our findings will inspire further exploration of vocal complexity across different species and pave the way for future discoveries in animal communication,” Erb said.