I'm developing an audio classification project with four classes using an RNN with LSTM. While the model performs well in classifying audio in silent environments, it struggles with noisy situations like crowds or disturbances. How can I train the model more robustly to accurately predict classifications in such challenging environments?
Categories
-
Digital Fabrication
Digital Fabrication Techniques
3D PrintingLaser CuttingPCB DesigningCNC Machining -
Events & Hackathons
A Place where you can share and find events and hackathons
HackClub: HackCamp 2020MakerChat -
MakerCuriosity
MakerCuriosity is a podcast series by MakerGram where we will be discussing about new boards, sensors, languages and many other things. There will be one new episode on each Monday.