Assessment of subjective audio quality from EEG brain responses using time-space-frequency analysis

In this paper, we consider the problem of quantifying changes in the perceived quality of audio by directly measuring the brainwave responses of human subjects using a highresolution electro-encephelogram (EEG). Specifically, human subjects are presented with audio whose quality varies with time while being monitored by a 128-channel EEG; some of the time, they move a slider bar up and down to indicate their perception of the changing quality while at other times they listen passively. Our focus here is to identify low-level features in the brainwave responses that correlate well with temporal quality variations across multiple base audio sequences and different test subjects with our ultimate goal being to implement a classifier based on such features. The results presented here attempt to quantify the quality classification performance versus the perceptual uncertainty of the subjective data. We find that the proposed approach is much more effective in estimating the perceptual quality for one of the two distortion types considered, frequency truncation, than it is for the other type, scalar quantization.