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.

132 pages

Return to: SCS Technical Report Collection
School of Computer Science

This page maintained by reports@cs.cmu.edu