Musical sound separation systems attempt to separate individual musical sources from sound mixtures. The human auditory system gives us the extraordinary capability of identifying instruments being played (pitched and non-pitched) from a piece of music and also hearing the rhythm/melody of the individual instrument being played. This task appears ‘automatic’ to us but has proved to be very difficult to replicate in computational systems. Many methods have been developed recently for addressing this challenging source separation problem. They can be broadly classified into two categories, respectively, statistical learning based techniques such as independent component analysis (ICA) and non-negative matrix/tensor factorization (NMF/NTF), and computational auditory scene analysis (CASA) based techniques.