Ning Hu

Automatic Construction of Synthetic Musical Instruments and Performers Degree Type: Ph.D. in Computer Science
Advisor(s): Roger Dannenberg
Graduated: August 2013

Abstract:

This thesis describes an approach to create high-quality music synthesis by automatically constructing an instrument model and a performance model; the latter module generates control signals from score input and drives the former module to produce synthetic instrumental sounds. By designing and applying appropriate machine learning techniques as well as domain knowledge, the instrument model and the performance model are constructed from acoustic examples and their corresponding scores for a musical instrument. The automated model is able to synthesize realistic instrumental performances from scores.

Thesis Committee:
Roger B. Dannenberg (Chair)
Richard M. Stern
Daniel D. Sleator
David Wessel (U.C. Berkeley)

Frank Pfenning, Head, Computer Science Department
Randy Bryant, Dean, School of Computer Science

Keywords:
Computer Music, Musical Instrument Synthesis, Machine Learning