Structured coding for content based interactive audio

The paper addresses the dual problem of audio coding for compression and retrieval. Because of the sheer volume of multimedia data, much research effort has focused on coding techniques for the compression of this data. However, being able to store large amounts of data in a compact fashion has limited application if there is no meaningful way to access and interact with them. Traditionally, these two issues have been treated separately resulting in many problems for multimedia data management. The authors have proposed a solution to these problems for audio by developing a compact, perceptually based, structured audio representation that provides explicit support for content based retrieval, browsing and other interactions. In addition, the representation offers potential for compressed data storage. The paper outlines a coding scheme based on the representation and reports the compression results