Faculty of Electrical & Computer Engineering, University of Tabriz, 51666-15813, Tabriz, Iran.
Sci Rep. 2021 Jul 29;11(1):15497. doi: 10.1038/s41598-021-94876-0.
The cocktail party phenomenon describes the ability of the human brain to focus auditory attention on a particular stimulus while ignoring other acoustic events. Selective auditory attention detection (SAAD) is an important issue in the development of brain-computer interface systems and cocktail party processors. This paper proposes a new dynamic attention detection system to process the temporal evolution of the input signal. The proposed dynamic SAAD is modeled as a sequential decision-making problem, which is solved by recurrent neural network (RNN) and reinforcement learning methods of Q-learning and deep Q-learning. Among different dynamic learning approaches, the evaluation results show that the deep Q-learning approach with RNN as agent provides the highest classification accuracy (94.2%) with the least detection delay. The proposed SAAD system is advantageous, in the sense that the detection of attention is performed dynamically for the sequential inputs. Also, the system has the potential to be used in scenarios, where the attention of the listener might be switched in time in the presence of various acoustic events.
鸡尾酒会现象描述了人类大脑将听觉注意力集中在特定刺激上而忽略其他声音事件的能力。选择性听觉注意力检测（SAAD）是脑机接口系统和鸡尾酒会处理器发展中的一个重要问题。本文提出了一种新的动态注意力检测系统来处理输入信号的时间演变。所提出的动态 SAAD 被建模为一个序列决策问题，通过递归神经网络（RNN）和 Q-learning 以及深度 Q-learning 等强化学习方法来解决。在不同的动态学习方法中，评估结果表明，使用 RNN 作为智能体的深度 Q-learning 方法提供了最高的分类准确率（94.2%）和最小的检测延迟。所提出的 SAAD 系统具有优势，因为它可以对顺序输入进行动态的注意力检测。此外，该系统有可能用于在存在各种声音事件的情况下，听众的注意力可能会随时间切换的场景。
