The concept of the audiobook is about to go to another level.
The TransProse project uses an experimental software program to "read" the text of a novel and determine the frequency and intensity of different emotions, based on language and word cues. Those emotional cues are then transposed into piano pieces that follow the narrative of the story chronologically.
TransProse is a collaboration between Hannah Davis, a programmer and musician based in New York City, and Saif Mohammad, a computational linguistics expert with the National Research Council Canada. They recently presented their paper, "Generating Music From Literature," at the European Chapter of the Association for Computational Linguistics (EACL) event in Sweden.
DNews: The Coolest Things Sound Waves Do
TransProse works by analyzing the text of a novel and determining the densities of eight different emotions - anger, anticipation, disgust, fear, joy, sadness, surprise and trust. The relative densities of each emotion determine key, tempo, notes and octaves. The musical piece is then structured to follow the sequence of the novel, broken into beginning, early middle, late middle and end sections.