Spatial Cues Gradient in Time Domain Based Audio Attention Computational Model

Authors

Hang Bo, School of Mathematics and Computer Science, Hubei University of Arts and Science, Xiangyang 441053, China;
Wang Yi, School of Mathematics and Computer Science, Hubei University of Arts and Science, Xiangyang 441053, China;
Changqing Kang, School of Mathematics and Computer Science, Hubei University of Arts and Science, Xiangyang 441053, China;
Huang Jian, School of Mathematics and Computer Science, Hubei University of Arts and Science, Xiangyang 441053, China;

Abstract

Abstract: In virtual reality audio, sound source whose directions change rapidly should have higher attention level. But present bottom-up audio attention computational models extract the underlying characteristics of single channel audio such as energy, pitch, zero crossing rate etc., which can not effectively express the audio attention caused by such signals. To solve this problem, based on the psychological principles that spatial information affects attention, a model was proposed to introduce the short-term spatial gradient cues to measure the attention caused by the single audio source space direction changing. Compared to the traditional audio attention computational model, the recall of detection of attention audio events increased 4.5 percentage points in experiments.

Recommended Citation

Bo, Hang; Yi, Wang; Kang, Changqing; and Jian, Huang (2020) "Spatial Cues Gradient in Time Domain Based Audio Attention Computational Model," Journal of System Simulation: Vol. 28: Iss. 10, Article 12.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss10/12

First Page

2369

Revised Date

2016-07-14

DOI Link

https://doi.org/

Last Page

2377

CLC

TP391.9

Recommended Citation

Hang Bo, Wang Yi, Kang Changqing, Huang Jian. Spatial Cues Gradient in Time Domain Based Audio Attention Computational Model[J]. Journal of System Simulation, 2016, 28(10): 2369-2377.