Abstract
To improve the effect of the content-based songs retrieval system, this paper proposes a audio denoising algorithm based on adaptive wavelet soft-threshold which on the basis of the gain factor of linear filter system in the wavelet domain and the wavelet coefficients teager energy operator (AWSTD_GF&TEO). The algorithm integrates the gain factor of linear filter system and nonlinear energy operator with conventional wavelet soft-threshold function. Experiments show that the algorithm has significant outcome in inhibiting Gaussian white noise and pink noise in audio samples and improving the accuracy of songs retrieval system.