Skip to main content
Fig. 3 | Human-centric Computing and Information Sciences

Fig. 3

From: An audio attention computational model based on information entropy of two channels and exponential moving average

Fig. 3

An illustration of waveform and attention graph of signal 1. The region marked in red is the area of interest and marked in orange is the non-interest area in d. In contrast to Kayser model which extracts contrast characters from the spectrum of audio signal in multi-scale, the proposed attention model based on information entropy and exponential moving average smooth reflects the value change of audio attention in the time domain

Back to article page