Latent Structure in Music

Combining methodologies from machine learning and deep learning, music information retrieval, and information theory, this project aims to create tools to analyze and extract latent structure and syntax in music in order to answer fundamental questions pertaining to meter, scale structures and harmony. Corpora include musical scores, music performance data, audio multitrack recordings, birdsong, and video and motion capture data. 

Featured publications

Polak, Rainer*, Nori Jacoby*, and Justin London*. "Both isochronous and non-isochronous metrical subdivision afford precise and stable ensemble entrainment: A corpus study of Malian jembe drumming." Frontiers in Auditory Neuroscience, DOI: 10.3389/fnins.2016.00285      *Equal Contribution

Jacoby, Nori, Naftali Tishby, and Dmitri Tymoczko. "An Information theoretic approach to chord categorization and functional harmony." Journal of New Music Research, DOI: 10.1080/09298215.2015.1036888