Acoustic Scene Classification (ASC) is a task that classifies a scene according to environmental acoustic signals. Audios collected from different cities and devices often exhibit biases in feature distributions, which may negatively impact ASC performance. Taking the city and device of the audio collection as two types of data domain, this paper attempts to disentangle the audio features of each domain to remove the related feature biases. A dual-alignment framework is proposed to generalize the ASC system on new devices or cities, by aligning boundaries across domains and decision boundaries within each domain. During the alignment, the maximum classifier discrepancy and gradient reversed layer are used for the feature disentanglement of scene, city and device, while four candidate domain classifiers are proposed to explore the optimal solution of feature disentanglement. To evaluate the dual-alignment framework, three experiments of biased ASC tasks are designed: 1) cross-city ASC in new cities; 2) cross-device ASC in new devices; 3) cross-city-device ASC in new cities and new devices. Results demonstrate the superiority of the proposed framework, showcasing performance improvements of 0.9%, 19.8%, and 10.7% on classification accuracy, respectively. The effectiveness of the proposed feature disentanglement approach is further evaluated in both biased and unbiased ASC problems, and the results demonstrate that better-disentangled audio features can lead to a more robust ASC system across different devices and cities. This paper advocates for the integration of feature disentanglement in ASC systems to achieve more reliable performance.

Steady-state visual evoked potentials (SSVEPs) have been widely applied in brain–computer interfaces, cognitive and clinical neuroscience study. Recently, 40-Hz flickering induced brainwave entrainment (BWE) was used to intervene cognition and aging-related diseases, such as Alzheimer’s disease (AD), vascular cognitive impairment, and phobic anxiety, through 1-h-long visual stimulations. The mechanism of action was believed to induce gamma oscillation in related brain regions. According to our knowledge, the amplitude of BWE at 40 Hz through a prolonged visual stimulation has not been reported. Therefore, we recorded electroencephalogram (EEG) signal induced by a high refreshing rate monitor in 50 healthy subjects. We observed that the response of BWE varied among subjects and fluctuated over time. The relationship between 40-Hz BWE and mental state was analyzed by the brainwave band ratio and signal entropies. We found that the amplitude of BWE was inverse proportionally to brainwave bandα/βratio and correlated with the sample entropy of the recorded EEG, which further connected the BWE response to the fatigue level of the subjects.We also demonstrated that a 1-min stimulation test before the 1-h-long visual stimulation was able to predict the amplitude of BWE. Finally, we showed that the measuredα/βandθ/βratios of EEG were not changed significantly before and after the 1-h-long stimulation. Our experimental results provided database for prolonged BWE, which is beneficial for the design of BWE treatment.

Sketch recognition is essential in sketch-related researches. Different from the natural image, the sparse pixel distribution of sketch discards the visual texture which encourages researchers to explore the temporal information of sketch. Using of million-scale datasets, we explore the invariable structure and specific order of strokes in sketch. Prior works based on Recurrent Neural Network (RNN) output different features with changed stroke orders. In particular, we adopt a novel method by employing a Graph Convolutional Network (GCN) to extract invariable structural feature under any orders of strokes. Compared with traditional comprehension of sketch, we further split the temporal information of sketch into two types of feature, invariable structural feature (ISF) and drawing habits feature (DHF) with the aim of finer feature extraction in temporal information. We propose a two-branch GCN-RNN network, Sketch-SNet, to extract two types of feature respectively. The GCN branch is used to extract the ISF through receiving various shuffled strokes of an input sketch. The RNN branch takes the original order to extract DHF by learning the pattern of strokes' order. Extensive experiments on the Quick-Draw dataset demonstrate that our further subdivision of temporal information improves the performance of sketch recognition which surpasses state-of-the-art by a large margin.