A combination of traditional recording methods and AI analysis helped in identifying three distinct variations within the long calls of primates. This new finding suggests that their vocalisations might be even more intricate than previously understood, a new study published in PeerJ Life & Environment says.
Orangutans are the largest tree-dwelling mammal and primarily eat insects and flowers. They are also known for complex social behaviour and communication.
Also read:Sun releases strongest X-ray flares since 2005, scientists warn massive sunspot yet to burst
Study co-author and Cornell University primatologist Wendy Erb said in a statement, “Our research aimed to unravel the intricacy of orangutan long calls, which play a crucial role in their communication across distances in the dense rainforests of Indonesia.”
“In the past three years, we have built hundreds of long call recordings, which are revealing an enthralling array of vocal diversity,” said Erb.
Known for their loud nature, long calls are vocalisations produced by male primates. These sounds serve as communication tools across long distances to connect with others. Previous research had compiled a 'dictionary' of the different 'pulses' within these calls.
Building on this foundation, a new study led by Dr Lisa Erb aimed to achieve three key objectives:
1) Identify the exact number of distinct pulse types.
2) Pinpoint the features that differentiate them.
3) Assess the degree of variation within these pulse types.
With the help of recorded video and audio sources, Erb and his team used machine learning to carefully analyse the long calls of 13 individual orangutans.
“Through a combination of supervised and unsupervised methods, we identified three distinct pulse types that were well differentiated by both humans and machines,” said Erb.
"This research advances our understanding of how orangutans communicate. However, it islikely just the tip of the iceberg. The orangutans' vocal repertoire may be much richer than we currently recognise, highlighting the remarkable complexity of their vocal system," adds Erb.
According to the team, the pulses are not just random noises; it reveals the power in collaborating across scientific disciplines and combining traditional research methods with advances in AI.
(With inputs from agencies)