AI Insight
This study demonstrates that distinguishing between acoustic and expectation-related representations within artificial neural networks (ANNs) improves the ability to identify music from EEG brain activity. Models pretrained on either type of representation outperformed non-pretrained baselines, and combining both yielded complementary performance gains exceeding those achieved by ensemble methods based on random initialization alone. Notably, the expectation representation was derived directly from raw audio signals without manual labels, capturing predictive structure beyond basic features like onset or pitch.
Why it matters
These findings advance neural decoding of music perception and could contribute to the development of general-purpose EEG models, with potential applications in brain-computer interfaces, cognitive neuroscience research, and music cognition studies.
arXiv:2603.03190v3 Announce Type: replace-cross
Abstract: During music listening, cortical activity encodes both acoustic and expectation-related information. Prior work has shown that ANN representations resemble cortical representations and can serve as supervisory signals for EEG recognition. Here we show that distinguishing acoustic and expectation-related ANN representations as teacher targets improves EEG-based music identification. Models pretrained to predict either representation outperform non-pretrained baselines, and combining them yields complementary gains that exceed strong seed ensembles formed by varying random initializations. These findings show that teacher representation type shapes downstream performance and that representation learning can be guided by neural encoding. This work points toward advances in predictive music cognition and neural decoding. Our expectation representation, computed directly from raw signals without manual labels, reflects predictive structure beyond onset or pitch, enabling investigation of multilayer predictive encoding across diverse stimuli. Its scalability to large, diverse datasets further suggests potential for developing general-purpose EEG models grounded in cortical encoding principles.