In 2025 we will leverage AI and machine learning to make real progress in understanding animal communication, answering a question that has puzzled humans for as long as we have existed: “What do animals tell each other? Are you saying?” Recent Coler-Doolittle AwardOffering cash rewards of up to half a million dollars for scientists who “crack the code” is a sign of confidence that recent technological developments in machine learning and large language models (LLM) are bringing this goal within our reach.
Many research groups have been working for years on algorithms to understand animal sounds. For example, Project SETI is decoding Click trains of sperm whales and songs of humpbacksThese modern machine learning tools require very large amounts of data, and until now, this amount of high-quality and well-annotated data has been lacking.
Consider an LLM like ChatGPT that has training data available that includes the entire text available on the internet. Such information on animal communication was not previously available. It's not like the human data corpora are of much greater magnitude than the data we have for wild animals: over 500 GB of words were used to train GPT-3, while just over 8,000 of the codas were used. Was used. For Project SETI's recent analysis of sperm whale communications (or vocalizations).
Additionally, when working with human language, we already Know What is being said? We also know what constitutes a “word”, which is a huge advantage in interpreting animal communication, where scientists rarely know whether a particular wolf howl means, for example, another wolf howl. Something different from a howl, or even what wolves consider a howl. Somehow similar to “word” in human language.
Nonetheless, 2025 will bring new advances in both the amount of animal communication data available to scientists and the type and power of AI algorithms that can be applied to that data. Automated recording of animal sounds has been placed within easy reach of every scientific research group, with the popularity of low-cost recording devices such as the Audiomoth increasing.
Large-scale datasets are now coming online, as recorders can be left in the field, allowing the sounds of gibbons or birds in the forest to be heard 24/7, over long periods of time. There were times when it was impossible to manage such a large-scale dataset manually. Now, new automatic recognition algorithms based on convolutional neural networks can run through thousands of hours of recordings, pick out animal sounds and cluster them into different types according to their natural acoustic characteristics.
Once those large animal datasets become available, new analytical algorithms become a possibility, such as using deep neural networks to find hidden structure in sequences of animal vocalizations that correspond to meaningful structure in human language. It is possible
However, the basic question that remains unclear is what exactly are we expected to do with these animal sounds? Some organizations, such as Interspecies.io, have stated their goal quite clearly, “converting signals from one species into coherent signals for another species.” In other words, to Translation Animal communication in human language. Yet most scientists agree that non-human animals have no true language of their own – at least not in the way we humans have language.
The Caller Dolittle Prize is a bit more sophisticated, seeking to “find a way to communicate with or understand an organism.” Interpreting is a slightly less ambitious goal than translating, considering the possibility that animals may not actually have a language that can be translated. Today we do not know how much or how little information animals communicate among themselves. In 2025, humanity will have the ability to surpass not only how much animals say, but also our understanding of what they are actually saying to each other.