Weekly Meeting - November 14: Big Data Techniques May Transform How We Understand, Create, and Interact With Music

Speaker:   Alfred Hero is the John H. Holland Distinguished University Professor of Electrical Engineering and Computer Science, and the R. Jamison and Betty Williams Professor of Engineering, at the University of Michigan. He is also Co-Director of the Michigan Institute for Data Science at the University.

Data-based metrics are transforming many aspects of life. As the Facebook scandal involving Cambridge Analytica recently reminded us in the case of politics, these developments are not always positive. However, big data can also expand out knowledge base in beneficial ways.The University of Michigan Institute for Data Science has launched four research initiatives that apply machine learning and data mining to the study of music theory, music performance, social media based music making, and the connection between words and music. Jason Corey, Associate Dean for Research and Graduate Studies at the School of Music Theater & Dance, believes the results will broaden and deepen our understanding of the complexities of how music is developed and experienced. The first research project will focus on crowdsourced music making and performance, seeking to discover patterns in audience participation and engagement; the results promise to be relevant to the development of new tools for music education. The second research project will develop and analyze a library of digitized performances of Bach’s Trio Sonatas; applying novel algorithms to study the music’s structure, different performances will be compared to determine which features make a performance artistic. The third research project will develop a data science network that connects language and music; tools will be developed that can produce musical interpretations of texts based on content and emotion, so that any text can be transmuted into music. The fourth research project will combine music theory and computational analysis to compare the melodies of music across six cultures (including Indian and Irish folk songs as well as Bach and Mozart) to identify commonalities in how music is structured cross-culturally.