WATCH IT IN ACTION
AudioLabs studies piano concertos stems
Working with AudioShake
The team at AudioLabs investigated specific source separation problems when isolating the recordings of piano concertos from full orchestras performances.
Challenges included the significant overlap between the piano and the orchestra both in time and frequency, and the lack of multitrack recordings available for training sound separation on orchestral pieces.
Harnessing AudioShake for the isolations, AudioLabs found that our models yielded the highest quality stems, encompassing both the piano and residual instruments representing the orchestra.
“It's remarkable to witness the substantial advancements that deep learning has brought to audio source separation, even in challenging scenarios. During our piano concerto experiments, 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.”
Meinard Müller
Professor for Semantic Audio Processing, AudioLabs
Get in touch.