Understanding the communication systems of non-human animals is a scientific challenge that bridges biology, linguistics, and machine learning. It involves making sense of not only the sounds animals produce but also how they influence and drive group behaviors and gives us insights into the cognition and intelligence of other species. In this talk, I will present some recent progress towards deciphering the structure of naturally occurring communication in the wild, with a focus on the vocalizations of sperm whales. I’ll share experiments that led to uncovering a unique combinatorial communication system in sperm whales—revealing a level of structural complexity and context sensitivity not previously recognized. I’ll conclude by outlining a broader research project: developing a generalizable, data-driven framework for decoding the communication systems of diverse species. This work opens the door to a deeper understanding of non-human intelligence and the underlying principles that govern its expression.

Pratyusha Sharma is a Senior Research Scientist at Microsoft Research and an incoming Assistant Professor at the Courant Institute and Center for Data Science at New York University. She did her PhD at MIT in the Computer Science and Artificial Intelligence Lab. She studies the interplay between language, sequential decision making and intelligence in natural and AI systems. Her research is published in interdisciplinary journals like Nature Communications, etc. and in academic conferences across machine learning, natural language processing, robotics, and marine biology. Her research has also been featured in articles in the New York Times, National Geographic Magazine, BBC, etc. She was recently a speaker at TED AI and was selected as a Rising Star in EECS, Data Science, and GenAI.