XClose

UCL Psychology and Language Sciences

Home
Menu

Speech Science Forum - Josh McDermott (MIT)

17 March 2022, 4:00 pm–5:30 pm

Speech Science Forum Logo

New Models of Human Speech Perception via Machine Learning

This event is free.

Event Information

Open to

All

Cost

Free

Organiser

Justin Lo

Abstract:

This talk will describe our group’s recent efforts to leverage contemporary machine learning to build neural network models of our auditory abilities and their instantiation in the brain, with a focus on speech and voice recognition. Such models have enabled a qualitative step forward in our ability to account for real-world auditory behavior, to understand its dependence on peripheral neural coding, and to illuminate function within auditory cortex. But they also exhibit substantial discrepancies with human perceptual systems that we are currently trying to understand and eliminate.

About the Speaker

Josh McDermott

at Massachusetts Institute of Technology

More about Josh McDermott