Learning Bayesian Statistics cover image

#40 Bayesian Stats for the Speech & Language Sciences, with Allison Hilger and Timo Roettger

Learning Bayesian Statistics

00:00

How to Choose the Right Models for Speech Representation?

Most of them, the main type of modals that are used in in speech sciences are generalizelino models. And now i'm wondering, what are most changing parts when you work with those kinds of models? Inow, are they usually hard to feed or or prayors, hard to choose? Like, what's usually your great problem? I mean, as i said early, arit is all linear regression and aggression. Linear regression human speech, or speech representations, we still poorly understand. We often lick good quantitative models. O for example, something that is very common is that ther are systematic individual differences between speakers and listeners,. So the variance related to speakers is not caution

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app