Christopher Kermorvant

Title: Large-scale handwriting recognition: implementation in historical
document processing projects

Prem Natarajan

Title: Frontiers of Fair and Accessible (Conversational) AI

Abstract : In this talk, I will share my perspective on making conversational AI more inclusive and accessible through advances in natural language understanding, speech recognition, and by incorporating interaction affordances that make conversational AI more useful for everyone. I will start with a brief overview of accessibility considerations and some Alexa-powered user experiences that address those considerations. That overview will be followed by a description of some of our recent and ongoing AI/ML work in natural language understanding (Alexa Teacher Model) and in ASR with a focus on achieving fairness and improving accessibility at scale. I will conclude with a brief mention of our engagements with academia, including through the Alexa Prize and through the release of publicly available datasets and associated research tasks.