Oompa Loompa and How to Save Lives Using Speech to Text
I am going to talk about how we at Tenfifty in collaboration with The Swedish Maritime Administration use AI to help the rescue leaders working at the Joint Rescue Co-ordination Centre (JRCC) to save lives around the Swedish coastline. The project named Heimdall is set out to detect emergency messages sent using VHF around the Swedish coastline. I will talk about how open source can be used to outperform existing solutions as well as how big of an impact the noisy audio as well as the domain has on existing models.
Niclas is a former software engineering student from Chalmers now working as Data Scientist at Tenfifty in Gothenburg since 2021. He works with applied Machine Learning to solve real-world problems for customers every day. Niclas co-authored the thesis “Automatic Emergency Detection in Naval VHF Transmissions” at Tenfifty and has since worked with the integration of the theory into practice.
