AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Learn a Language Model From Text
Do you know if this is a common problem today? So trying to go right from the audio to a language model. And could we potentially incorporate that as another signal into just learning a language model also from text? Yeah, so as far as I know, I haven't been in the like core speech field for a while. But there is a lot of really interesting work going on, you know, right now on better unsupervised learning methods to learn acoustic representations.