The goal of audio scene recognition is to identify scenes in which audio clips were recorded, depending on the typical acoustic feature these scenes share.

For unknown environments,a natural scene recognition approach based on visual local salient regions is presented.

The present paper addresses, using scene recognition task, solely on the basis of behavioral data.

Having discussed various audio features and their extracting methods,we bring forward a new method for audio scene segmentation,according to the features of six kinds of audio signal types(silence,music,environmental sound,pure speech,speech with music and speech with environmental sound)to segment audio stream.