Deep Learning of Human Perception in Audio Event Classification
This work addresses audio event classification for applications in human-computer interaction, but it is incremental as it combines existing deep learning models with EEG data.
The paper tackled audio event classification by integrating human perception via EEG signals, showing that using EEG data can improve classification performance and that correlations between audio stimuli and EEG can be learned to enhance understanding.
In this paper, we introduce our recent studies on human perception in audio event classification by different deep learning models. In particular, the pre-trained model VGGish is used as feature extractor to process audio data, and DenseNet is trained by and used as feature extractor for our electroencephalography (EEG) data. The correlation between audio stimuli and EEG is learned in a shared space. In the experiments, we record brain activities (EEG signals) of several subjects while they are listening to music events of 8 audio categories selected from Google AudioSet, using a 16-channel EEG headset with active electrodes. Our experimental results demonstrate that i) audio event classification can be improved by exploiting the power of human perception, and ii) the correlation between audio stimuli and EEG can be learned to complement audio event understanding.