Summary: AUDIO ANALOGIES: CREATING NEW MUSIC FROM AN EXISTING
PERFORMANCE BY CONCATENATIVE SYNTHESIS
Ian Simon
University of Washington
Sumit Basu
Microsoft Research
David Salesin
Microsoft Research
Maneesh Agrawala
Microsoft Research
ABSTRACT
This paper describes a method for creating new music by
concatenative synthesis. Given a MIDI score and an au-
dio recording of an example piece of monophonic music,
our method synthesizes audio to correspond with a new
MIDI score. The algorithm we use is based on concate-
native synthesis, commonly used for generating speech.
Two versions of our algorithm are explored, one in which
individual notes from the example piece are concatenated,
and one in which pairs of adjacent notes from the example

Source: Agrawala, Maneesh - Department of Electrical Engineering and Computer Sciences, University of California at Berkeley
Washington at Seattle, University of - Department of Computer Science and Engineering, Graphics and Imaging Laboratory

Collections: Computer Technologies and Information Sciences