Source extraction from two-channel mixtures by joint cosine packet analysis

This paper describes novel, computationally efficient approaches to source separation of underdetermined instantaneous two-channel mixtures. A best basis algorithm is applied to trees of local cosine bases to determine a sparse transform. We assume that the mixing parameters are known and focus on demixing sources by binary time-frequency masking. We describe a method for deriving a best local cosine basis from the mixtures by minimising an l1 norm cost function. This basis is adapted to the input of the masking process. Then, we investigate how to increase sparsity by adapting local cosine bases to the expected output of a single source instead of to the input mixtures. The heuristically derived cost function maximises the energy of the transform coefficients associated with a particular direction. Experiments on a mixture of four musical instruments are performed, and results are compared. It is shown that local cosine bases can give better results than fixed-basis representations.