The Music, Mind and Machine Group at the MIT Media
Laboratory is developing new audio technologies for future
interactive media applications. This ranges from automatic
sensing of features in existing audio content to extremely
compact representations of sound for efficient transmission
and control in a networked future.
Feature extraction is aimed at finding the relevant
parameters of musical audio that will assist web-based
queries and searches of content, or alternatively to gain
sufficient understanding of specific audio examples to
enable their modification and restructuring.
We have contributed the core compact representation of the
MPEG-4 audio standard, enabling full client-side rendering
of structured audio and 3D effects from symbolic audio
descriptions, and are developing automatic methods for
synthesizing target sounds.
We have developed novel methods of automatic signal
separation, and new methods of directing laser-like beams
of audio in specific directions.
We have developed net-based methods of music production and
performance, and are key participants in the MPEG-7
web-oriented archiving and searching initiatives.
This group envisages a new future of audio technologies and
interactive applications that will change the way music is
conceived, created, transmitted and experienced, and we are
active participants in every facet of this exciting future.