Meetings
Meetings are open to the public and we encourage anyone to join: beginners, practitioners, researchers — all are welcome.
Current schedule
| Term | Fall 2026 |
|---|---|
| Day | Most weeks on Thursday |
| Time | 7:00 pm – 8:00 pm |
| Room | TBD |
| Online | Join on Zoom |
Let us know if you would like to meet in person and we will find a room.
Next meeting
Intro to Projects — Thursday, October 1
Project check in and Reading Group: A Dimensional Model of Interaction Style Variation in Spoken Dialog — Thursday, October 8, 7:00 pm
What happens at a meeting
Our meetings generally revolve around:
- Project updates from lab members
- Open discussion and problem-solving
- Short tutorials on tools and techniques
- Coverage of the latest research in our fields of study
Reading Groups
Throughout the semester, we host reading groups to explore current developments in the industry.
Why should you attend?
- Discover topics you are interested in and want to work on.
- Form ideas for research projects that you’re passionate about.
- Practice your skills in presenting and speaking about research.
This week’s paper
A Dimensional Model of Interaction Style Variation in Spoken Dialog — Nigel G. Ward and Jonathan E. Avila, Speech Communication, 2023. Presented by Dain Brownlow.
Ward and Avila apply Principal Component Analysis to 84 prosodic features drawn from the Switchboard corpus to build an eight-dimensional model of how interaction style varies in spoken dialog. They argue that dialog systems should be able to adapt their style the way people do, and report a surprising result: individual style tendencies turn out to be weak enough that a model built on them outperforms a speaker-independent model by only 3.6 percent.
About the presenter
Dain Brownlow is a Computer Science undergraduate at the University of San Francisco (Class of 2027) and a research assistant in the MAGICS Lab, where he works on computational linguistics. His current project studies conversational style in large-scale speech corpora, testing sociolinguistic style frameworks using Python-based pipelines, encoder models for learned representations, and statistical methods such as PCA and Gaussian mixture clustering.
Questions?
Contact the lab manager and they’ll point you in the right direction.