In this talk, Abraham Sanders will explore how Audio Language Models work and how to use them, as well as cover tokenization of audio waveforms; creation of autoregressive language models; and applying audio language models to common tasks such as Automatic Speech Recognition (ASR), Text-To-Speech (TTS) and Speech-To-Speech Machine Translation. He will conclude with a discussion of future-focused applications, including text-guided music generation and full-duplex spoken dialogue agents.

 Rensselaer's School of Architecture is proud to announce that students Maddie Mast and Sarah Weber have been selected for the 2024 Metropolis Future 100 award, a highly-selective award that showcases the nation's most exceptional architecture students. According to Metropolis, "each year, Metropolis sets out to designate the top graduating architecture and interior design students in the United States and Canada. Nominated by their instructors and mentors, these 50 interior design and 50 architecture students were chosen by the Metropolis team."