2023 Spring Faculty Meeting

Schedule

Time	TOPIC	zoom link
3:45 p.m.	Program Meeting for Healthcare Systems Engineering	https://wse.zoom.us/j/99426784334
4 to 5 p.m.	Program Meetings	Applied and Computational Mathematics Applied Biomedical Engineering Applied Physics Civil Engineering Computer Science // Cybersecurity // (AI will be discussed the last 15 minutes of this program meeting) Electrical and Computer Engineering Engineering Management Environmental Engineering, Science, and Management Financial Mathematics Information Systems Engineering Materials Science and Engineering Systems Engineering
5 to 5:15 p.m.	Welcome and EP Update	wse.zoom.us/j/92308550072
5:15 to 5:20 p.m.	Faculty Affairs at EP	wse.zoom.us/j/92308550072
5:20 to 5:25 p.m.	Faculty Forward	wse.zoom.us/j/92308550072
5:25 to 5:50 p.m.	2022 Faculty Awards Ceremony	wse.zoom.us/j/92308550072
5:50 to 6:20 p.m.	Keynote Address: Ariya Rastrow “The All-Neural Era: Progress in Speech Recognition Technology at Alexa”	wse.zoom.us/j/92308550072
6:20 to 6:35 p.m.	Keynote Q&A	wse.zoom.us/j/92308550072

Keynote

Ariya Rastrow, senior principal scientist for Alexa AI.

“The All-Neural Era: Progress in Speech Recognition Technology at Alexa”
Speech recognition technology is undergoing a dramatic shift, moving to an all-neural architecture, replacing the conventional stack of disjointly trained neural and non-neural sub-systems. The unified all-neural architecture improves SOTA accuracy, while also achieving superior memory and compute compression, enabling streaming low-latency speech recognition at the edge, where resources are constrained. The unified all-neural architecture, in conjunction with multi-task learning approaches, overhauls the boundary between the spoken language understanding (SLU) sub-components of voice AI assistants, including end-pointing, speaker segmentation, device-directed classification, and language identification and language understanding, allowing for a jointly trained unified stack that goes beyond a transcription-only task. In this talk, I give an overview of the existing challenges and our recent progress in addressing different aspects of adapting all-neural technology for production ASR for Alexa, the AI assistant that serves millions of customers daily.

Please Register Below

Disability Services

If you need accommodations, please request them using this link.

Thank you

As a thank you for your dedication to EP students, we would like to send you a Whiting School of Engineering umbrella. To order your umbrella, click here.

Questions?

If you have questions please email Joyce Richardson.