Matlab code for Learning a discriminative high-fidelity dictiona...

Sparse-representation-based single-channel source separation, in which an attempt is made to recover each source’s signal using its corresponding sub-dictionary, has attracted many scholars’ attention. The basic premise of this model is that each sub-dictionary possesses discriminative information about its corresponding source, and this information can be used to recover almost every sample from that source. However, in a more general sense, the samples from a source are composed not only of discriminative information but also common information shared with other sources. this package is used to constructing a union dictionary composed of source-specific sub-dictionaries and an additional sub-dictionary to improve the source separation performance.