“AudioShake was able to take those original tracks from the 1920s and 1930s and spit out isolated fiddle and isolate the piano It was a game changer, and it turned what I thought was at first an impossible, challenging project into one that was feasible."
"It's remarkable to witness the substantial advancements that deep learning has brought to audio source separation. I was deeply impressed by the performance of the AudioShake system, especially considering that it had never been trained on this type of data before."












