Source separation, stem separation or de-mixing are all different ways of referring to the same problem of recovering the mono-instruments tracks that were mixed together to produce a music file. Recently, the research team at Deezer released a free and open source software as well as trained models to perform multi-source separation of music, with state-of-the-art accuracy.
Expert software engineer with strong architectural skills and a deep concern about delivery and quality. I worked more than 10 years on high end projects using state of the art technologies and industrializing various research field at scale, including information retrival techniques, machine learning and audio signal processing using deep learning.
I will lead any innovation driven project from PoC to industrial standard, define robust architecture while complying with your ecosystem and mentoring your resources so they can grow.
