These are some of the projects that are typical of research and
development in Music and Technology at Carnegie Mellon.
is a sound synthesis and composition language offering a Lisp syntax as
well as an imperative language syntax and a powerful integrated
Nyquist is an elegant and powerful system based on functional
free, open source software for recording and editing
sounds. It is available for Mac OS X, Microsoft Windows, GNU/Linux, and
other operating systems. Audacity was originally designed and developed
by Roger Dannenberg and Dominic Mazzoni working in Carnegie Mellon’s
School of Computer Science Computer Music Project.
AuraRT is a
software framework for creating interactive multimedia software,
particularly advanced interactive music compositions. A subproject is
AuraFX, a flexible signal processor configurable by end-users.
Popular Music Systems
This project studies interfaces and systems for performing popular
music using computers as highly autonomous music performers. Research
includes methods to synchronize with human performers, communication
between human and computer performers, high-quality sound synthesis,
score display and annotation, and automating audio effects.
is a robotic bagpipe player. It plays an ordinary
set of bagpipes using an air compressor to provide air and
electro-magnetic devices to power the "fingers" that open and close
tone holes that determine the musical pitch.
(Dawen Liang’s Thesis)
As the high-capacity data storage devices (e.g. portable hard drives, and USB flash drives) become available to everyone, musicians are able to record all of their rehearsals and save them digitally. Given large amount of unlabeled and unorga- nized rehearsal recordings, manually organizing them can be a huge task. Therefore, managing music audio databases for practicing musicians automatically is a new and interesting challenge.
This thesis describes a systematic investigation to provide useful capabilities to musicians both in rehearsal and when practicing alone. The goal is to allow musicians to automatically record, organize, and retrieve rehearsal (and other) audio to facilitate review and practice (for example, playing along with difficult passages). In order to accomplish this task, three separate problems should be solved:
Given the original recordings,extract the music segments and get rid of the non-music parts. A novel music classification system based on Eigenmusic and Ad- aBoost classifier to separate rehearsal recordings into segments is proposed.
Given the music segments from the previous step, the system should be able to group the segments which belong to the same composition together. An unsu- pervised clustering and alignment process to organize segments is introduced.
Finally, an interactive user interface is required for musicians to easily access and compare the previous rehearsals. The thesis provides a digital music display interface that provides both graphical input and output in terms of conventional music notation.
The thesis will address each of these 3 problems and provide an implementation that works in practice. Some future work is also described.
© 2012 - Carnegie Mellon University
5000 Forbes Avenue - Pittsburgh PA, 15213-3815