An audio recognition method may comprising performing diffusion processing on a plurality of first feature points in a spectrogram of a to-be-recognized audio file to obtain a feature point map; searching in a spectrogram of a target audio file to determine whether the spectrogram of the target audio file comprises second feature points that respectively correspond to the diffused first feature points in the feature point map; and in response to determining that the spectrogram of the target audio file comprises the second feature points, determining that the to-be-recognized audio file is a part of the target audio file.