MIT Media Lab, E14-633
Music has been shown to be an essential part of the human experience---every known society engages in music. However, as universal as it may be, music has evolved into a variety of genres peculiar to particular cultures. In fact, people acquire musical skill, understanding, and appreciation specific to the music they have been exposed to. This process of enculturation builds mental structures that form the cognitive basis for musical expectation.
In this thesis, Sarkar argues that in order for machines to perform musical tasks like humans do, in particular to predict music, they need to be subjected to a similar kind of enculturation process by design. This work is grounded in an information theoretic framework that takes cultural context into account. He introduces a measure of melodic and rhythmic entropy to analyze the predictability of musical events as a function of prior musical exposure. Then he discusses computational models for music representation that are informed by genre-specific containers. Finally he proposes a software framework for automatic music prediction. The system extracts a lexicon of melodic and rhythmic primitives from audio, and generates a hierarchical grammar to represent the structure of a particular musical form. To improve prediction accuracy, context can be switched with cultural plug-ins that are designed for and trained by specific musical instruments, genres, and performance styles.
In controlled listening experiments a culture-specific design fares significantly better than a culture-agnostic one. Hence Sarkar's findings support the importance of computational enculturation for automatic music prediction. Furthermore he suggests that in order to sustain and cultivate the diversity of musical traditions around the world it is indispensable that we design culturally sensitive music technology.
Additional Featured Research By
(Unpublished) Music, Mind and Machine
Host/Chair: Barry L. Vercoe
Mitchel Resnick, Christopher D. Chafe (Stanford University)