SurpriseLSTM: Neural Modeling of Musical Expectation and Surprise in Monophonic Melodies

We introduce SurpriseLSTM, an LSTM network that predicts note-by-note surprisal in strictly monophonic, symbolic melodies. We conduct the first systematic comparisonsof a neural expectancy model against the symbolic IDyOM model and the audio-based AudioIC algorithm across five complementary validation paradigms: large-scale correlations on Western melody corpora, two-note pleasantness ratings, Bach-chorale surprise profiles, and the musicalWundt effect. SurpriseLSTM matches or exceeds the performance of IDyOM in aligning with human surprise judgments. A detailed context analysis reveals distinct differences in how neural and statistical models respond to authentic cadences versus non-cadential situations, with SurpriseLSTM showing superior containment rates and distribution fitting in predicting human scale degree expectations. These findings demonstrate that recurrent neural networks, trained on basic note-level features, can accurately capture the cognitive principles of statistical learning and probabilistic prediction in music perception. Code and a pre-trained model are available at https://github.com/lissenko/surprise-lstm.