In this paper, three sparse models for the human auditory system are proposed. Biological studies shows that the haircells in the inner ear of the auditory system generate sparse codes from the output of cochlea filterbank. Here, we employ two mathematical sparse representation methods, which are Orthogonal Matching Pursuit (OMP) and K Singular Value Decomposition (K-SVD), in three different strategies for sparse representation of the output of cochlea filterbank that is modeled by a Gammatone filterbank. Although, we use nearly 5 to 10 percent of the original signal's dimension for sparse representation, experimental results by evaluating reconstruction error and PESQ measures demonstrate good performance of these models in both clean and noisy conditions.