“…They adopt various perspectives, including performance recordings data [10], metadata (genre, composer, lyrics, etc. [11,12,13]), musical scores (MIDI [14], harmony and cadence [15], and piano notation [16,17]), information associated with fingering [18] or music analysis [19], other multimodal information [20,21], emotions [22,23], listening history [24], and performers' interpretations [25,26,27,28]. To the best of our knowledge, none have focused on human cognition, such as the experiences of playing or listening to a piece of music.…”