Generating Music from Literature Using Topic Extraction and Sentiment Analysis

This article presents Tambr, a new software for translating literature into sound using multiple synthesized voices selected for the way in which their timbre relates to the meaning and sentiment of the topics conveyed in the story. It achieves this by leveraging a large lexical semantic database to implement a machine-learning-based synthesizer search engine used to select the synthesizers whose meaning best reflects the ideas of the novel. Tambr uses sentiment analysis to generate the pitches, durations, and intervals of the output melodies in a way corresponding to the sentiment of the novel-implementing algorithmic composition of literature-based music at a level of musicality not previously explored.