Featured
- Get link
- Other Apps
A three year hunt for patterns hidden in the roars, sighs,
and other noises made by Indonesia's
orangutans has discovered 'a full spectrum' of complex vocalizations.
The breakthrough comes hot on the heels of other recent
discoveries further revealing the depth of the great ape's intelligence —
including one orangutan's practice of healing its own injuries with a self-prepared medicinal herb.
The research team reinforced their analysis by testing
artificial intelligence (AI)
detection methods against the painstaking work of biologists and bioacoustics
scientists, employing only their trained ears, intellects and measurement
tools.
The Cornell University-led team pooled together a dataset of
117 recorded 'long calls' made by 13 males of one particular species,
the Bornean orangutan, employing 46 acoustic measurements on 1,033
distinct pulses detected within those calls.
'These features would seem to greatly boost the potential
complexity of this signal,' they wrote, suggesting humanity might soon know
what the great apes are saying.
A Cornell-led team pooled together a dataset of 117 recorded 'long calls' made by 13 male orangutans - deploying 46 acoustic measurements on 1,033 pulses detected within the calls. The results appear to show higher 'potential complexity' in ape calls than previously realized© Provided by Daily Mail
As reported in the new study, published Tuesday in the
journal PeerJ
Life & Environment, the researchers found 'a continuous gradation of
sounds across phases and pulses,' suggesting orangutans can modulate their
voices very precisely.
All these distinct phases and pulses, the team wrote, can be
'combined into variable sequences within a single long call vocalization,'
meaning that the male apes' 'long calls' very likely communicate complex
messages to their distant ape peers.
'Our research aimed to unravel the complexities of orangutan
long calls, which play a crucial role in their communication across vast
distances in the dense rainforests of Indonesia,' the study's lead author Dr.
Wendy Erb said in a statement.
Related
video: Orangutan helps himself to cool drinks at the Rainforest
Discovery Centre in Sandakan (Dailymotion)
'We are fairly confident there is much complexity still to
unpack in this great ape's vocal system,' Dr. Erb opined.
A primatologist at Cornell's K. Lisa Yang Center for
Conservation Bioacoustics, Dr. Erb told Salon that the bioacoustics experts who study the
meaning behind animal sounds still lack 'a unifying framework for quantifying
complexity.'
As part of their effort to detect and classify the
orangutans' noises with AI, the team took parallel 'supervised' and
'unsupervised' machine learning approaches.
As part of their effort to detect and classify the orangutans' noises with AI, the team took parallel 'supervised' and 'unsupervised' machine learning approaches. Above, wave forms of the ape's various, distinct vocal pulses as published by the team in PeerJ Life & Environment© Provided by Daily Mail
The team used a state-of-the-art unsupervised machine learning algorithm, Uniform Manifold Approximation and Projection (UMAP), that had shown success decoding 'animal vocal repertoires' for the University of California, San Diego back in 2020.
The UMAP algorithm was further assisted by additional
statistical algorithms developed in the coding language R.
For their supervised machine learning, R-based code was also
used — but in all cases the apes' 1,033 unique vocal phases and pulses
were divided at random into a 60/40 split, where 60 percent was used to train
the AI, while the remaining 40 percent was used for testing the accuracy of its
freshly trained sorting ability.
'Through a combination of supervised and unsupervised
analytical methods,' as Dr. Erb summed it up, 'we identified three distinct
pulse types that were well differentiated by both humans and machines.'
The names of those three pulse types, as given by the
researchers to help steer future study, were: 'Roar' to define high-frequency
pulses, 'Sigh' meaning low-frequency pulses, and 'Intermediate' to catch any
and all pulses that fell between those two previous categories.
Dr. Erb and her colleagues took pains to emphasize that
these were only the limits of their current research, not the limits of what we
may one day learn about apes' vocal communication skills.
'Although many pulse types were not well differentiated by
humans or machines in this study,' they noted, 'we do not intend to suggest
that other workers were unable to make those distinctions or that orangutans
cannot perceive them.'
This ability to distinguish and differentiate between the
apparently myriad unique sounds that these large primates make, ultimately,
will be the next project for those hoping to one day understand and perhaps
speak with humanity's primate cousins.
'While our study represents a significant step forward in
understanding orangutan communication, there is still much to uncover,' Dr. Erb
admited.
'Orangutans may possess a far greater repertoire of sound
types than we have described, highlighting the complexity of their vocal
system.'
- Get link
- Other Apps
Popular Posts
- Get link
- Other Apps
- Get link
- Other Apps
Comments
Post a Comment