Using Deep Learning to Reconstruct High-Resolution Audio
Jeffrey Hetherly
3107

This question may stem from my ignorance​ of audio downsampling but what considerations did make regarding your downsampling vs damage that would occur 'in the wild’ for VoIP? Is there any insight as to how your manufactured training ‘damage' would generalize or is that more of a given due to how downsampling actually works in practice?

Like what you read? Give Cameron Scott White a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.