ugc_banner

What do those meowing and neighing mean? Will artificial intelligence tell us how animals communicate?

WION Web Team
New Delhi, IndiaUpdated: Mar 23, 2022, 06:35 PM IST
main img
Photograph:(Others)

Story highlights

With constant advancements in technology, there's is no exaggeration in saying that such results, where humans will be able to communicate with animals, are achievable in near future 

Have you ever wondered what if humans are able to communicate with animals and birds? With the help of the artificial intelligence (AI) algorithm, scientists recently revealed that they translated pig grunts into emotions for the first time. It could help them monitor animal wellbeing. 

Experts have claimed that the research, which was led by the University of Copenhagen, the ETH Zurich and France's National Research Institute for Agriculture, Food and Environment (INRAE) could also be used to better understand the emotions of other mammals. 

It looks like researchers are already working on it. As per a report published by The Wall Street Journal, it has been revealed that researchers are using AI to parse the "speech" of animals. 

The method will help scientists to create systems that decode animal sounds. For example, such algorithms might help to detect and monitor whale songs. So that the nearby ships can be alerted to avoid collisions. 

As quoted by WSJ, Oren Etzioni, who is an AI researcher and head of the Allen Institute for AI, said, "It is fascinating that the tools of artificial intelligence, specifically deep learning, which is the hot new thing, do seem to be the natural tools to study this other kind of 'A.I.'—animal intelligence." Allen Institute for AI is a nonprofit, which was set up by the late Microsoft co-founder Paul Allen. 

The report added that researchers on animal communication are using a branch of AI that "self-supervised learning". In recent years, self-supervised learning has proven effective for handling human language. 

Self-supervised learning (SSL) is a method of machine learning. It learns from unlabeled sample data. It can be regarded as an intermediate form between supervised and unsupervised learning. It is based on an artificial neural network.

As per the report, "self-supervised learning" shows promise as a way to process the immense quantities of recordings of animal communication, captured in laboratories as well as natural environments. 

With constant advancements in technology, there's is no exaggeration in saying that such results, where humans will be able to communicate with animals, are achievable in near future. 

We have seen certain examples, researchers at Cornell University and the Chemnitz University of Technology in Germany had developed an AI-based system, called BirdNET that can now recognise the calls of more than 3,000 different species of birds.