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.
Among the classic novels run through the TransProse system: Joseph Conrad's "Heart of Darkness," Lewis Carroll's "Alice in Wonderland" and Cormac McCarthy's "The Road."
Sound Waves Levitate, Move Objects In Three Directions
"The current version of TransProse is just the beginning of our investigation, and we don't claim to be making beautiful music yet," the team writes on the TransProse project page. "This iteration is a starting point to see if we could programmatically translate the basic emotions of a novel into a musical piece that holds the same basic emotional feeling."
It's an intriguing concept, but there are still a few bugs in the system, apparently. The team recently inputted Jane Austen's classic romance "Sense and Sensibility" and the algorithm spit out Side B of AC/DC's first album, "High Voltage."
We kid, we kid. Check out the project's music page for some sound files of the actual transposed literature.
Credit: Aleksander Yrovskih/Getty Images