Research Expertise and Interest

computational linguistics, machine learning, artificial intelligence, Generative AI, Deep Learning, speech processing, NLP, phonology, articulatory and acoustic phonetics, historical linguistics, Indo-European linguistics

Research Description

Gašper Beguš is an Assistant Professor at the Department of Linguistics at UC Berkeley.  Before coming to Berkeley, he was an Assistant Professor at the University of Washington and before that he graduated with a Ph.D. from Harvard. He combines machine learning and statistical modeling with neuroimaging and behavioral experiments to better understand how neural networks learn internal representations in speech and how humans learn to speak. He has worked and published on sound systems of various language families such as Indo-European, Caucasian, and Austronesian languages.

In a recent set of papers (here and here), he proposes that language acquisition can be modeled with Generative Adversarial Networks and propose a technique for exploring the relationship between learned representations and latent space in deep convolutional networks.

Dr. Beguš directs the Berkeley Speech and Computation Lab. Dr. Beguš also serves as the College Principal of the oldest residential college in the country, the Bowles Hall Residential College

In the News

A Race to Converse With, and Save, the Ocean’s Brainiest Eco-Predators

At the University of California, Berkeley, a real and more down-to-earth mission to decode an unknown form of communication is underway. Linguist Gasper Begus and computer scientist Shafi Goldwasser are part of an international team of researchers attempting interspecies communication with sperm whales by deciphering their deafening, 200-plus decibel clicking sounds, or codas.
Loading Class list ...