- About MET-lab
- Research projects
- K-12 education initiatives
Structured audio is a representation of sound content using symbolic or semantic information as a means of encoding (or representing) the data. It provides a framework to easily manipulate or transform content after it reaches the user.
A mixing engineer performs many minute changes to the volume and timbre of each instrument to produce a finished, polished song. This system uses statistical models to analyze the audio and generate the types of changes that the mixing engineer will perform to turn a set of raw tracks into a completed song.
Representing music and audio content within the structured audio framework facilitates creation of innovative applications that allow a user to interact with and control their music on a fundamental level.