"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."

"The resulting stems enabled me to seamlessly re-mix the audio material. To preserve the original atmosphere of the recording, I could smoothly switch between new stems and the original stereo mix while working, thus eliminating problematic moments We are at the beginning of the road where AI technology comes to …