Spatial audio cues based surveillance audio attention model
Bo Hang, Ruimin Hu · 2010
In this paper, we propose a bottom-up audio attention model based on spatial audio cues for unsupervised event detecting in stereo audio surveillance. Firstly, the spatial audio parameter Interaural Level Difference (ILD) is extracted to calculate and represent the attention events, which are caused by rapid moving sound source. Then an environment adaptive normalization is used to assess the normalized attention level. Experimental results demonstrate that our proposed audio attention model is effective for audio surveillance event detection.