Speaking with Animals? Yes, Machine Learning is Making it Possible

Artificial Intelligence and Machine Learning have helped us decode ancient languages, and now researchers are turning the same technique to help us understand our favorite animals. A California-based Earth Species Project (ESP) organization wants to harness the power of machine learning to decode non-human communication using a form of artificial intelligence called machine learning, and make all the know-how publicly available, thereby deepening our connection with other living species and helping to protect them.

ML might help us in translating animal communication in the coming decades. Understanding animal vocalizations has long been the subject of human fascination and study. AI and ML communication is not only about words but a lot more about tone, timing, context, and facial expressions too. AI-enhanced abilities to decode languages have reached a point where they could start to parse languages not spoken by anyone alive. And AI and ML can add value in helping researchers try to decode animal communication. The organization is working towards decoding animal communication and discovering a non-human language.

Can ML help us talk to animals?

ML can surely become a great tool in animal husbandry whether it be as part of research or industrial levels.  And also, to decode animal communication at least to an extent shortly optimistically. According to a study dolphins address, each other with signature whistles, and some songbirds can take elements of their calls and rearrange them to communicate different messages. But most experts stop short of calling it a language, as no animal communication meets all the criteria.

A further initiative – Project CETI (which stands for the Cetacean Translation Initiative) – plans to use ML to translate the communication of sperm whales. the goal is to develop tools that could be applied to the entire animal kingdom and to show that today's most cutting-edge technologies can be used to benefit not only humankind but other species on this planet. This project applies advanced machine learning and gentle robotics to decipher the communication of the world's most enigmatic ocean species: the sperm whale.

The AI-based model developed by ESP, which was tried on dolphin signature whistles, macaque coo calls, and bat vocalizations, worked best when the calls came from individuals that the model had been trained on. Another project involves using AI and ML to generate novel animal calls, with humpback whales as a test species. The novel calls – made by splitting vocalizations into micro-phonemes.

A further project aims to develop an algorithm that ascertains how many call types a species has at its command by applying self-supervised machine learning, which does not require any labeling of data by human experts to learn patterns. Meanwhile, another project seeks to understand automatically the functional meanings of vocalizations. We hope that the work ESP can do will provide new insights.