AI struggles to decipher 'animal language' because sound doesn't equal meaning, experts say
In recent years, numerous attempts have been made to use artificial intelligence to decipher the communication of bats, whales, birds and other animals. However, a new study led by a team of researchers from Tel Aviv University points to a fundamental problem with this approach: AI models focus on the physical properties of a sound, but this does not mean they understand the meaning attributed to…
Recent research by Tel Aviv University researchers reveals that artificial intelligence struggles to decipher animal language, according to a study published in Current Biology. The issue lies in the fact that AI models focus on the physical properties of sounds without considering the meaning they hold for the recipient animal.
While sounds that are similar acoustically may not necessarily convey the same message, sounds that appear different may still communicate the same information. The study, which analyzed toddler vocalizations, demonstrated that even advanced deep neural networks failed to classify the sounds according to their intended meaning or recognize urgency based on sequences of sounds.
To accurately understand animal communication, researchers argue that a combination of AI tools, behavioral observations, playback experiments, and measurements of brain activity are necessary. This approach acknowledges that each species has its own unique perceptual world, and understanding animal communication requires considering how the recipient perceives and responds to the sounds.
Written by urgent.news from Phys.org's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
