Speech recognition for Swedish - Jens Edlund, KTH

31 March: Speech recognition for Swedish
- Jens Edlund, KTH

A significant proportion of showcase applications of AI puts spoken language at their core: intelligent assistants, deep fakes, speech search, and automatic transcription, to mention a few. This seminar will highlight some of the factors that often go missing when speech is treated as e.g. a simple encoder-decoder problem, and why they are important. The seminar will also attempt to show why speech-centric research historically is truly interdisciplinary, and why it should remain that way

-- 

By practitioners, for practitioners

This is a bi-weekly webinar series for people who work with, or are interested in, NLP. The idea is to provide a platform for both academic researchers and industry practitioners to present, listen to, and discuss recent work in NLP. The main focus of the webinars is NLP development in Sweden and for the Swedish language, but international breakthroughs may also be discussed. 

Each webinar features an initial 45-minute presentation that covers recent work that in some sense is relevant for Swedish NLP, followed by 45 minutes of discussion.

Time: Wednesdays odd weeks 14:00-15:30

Read more and sign up here