Computing Structural Descriptions of Music through the Identification of Representative Excerpts from Audio Files

With the rapid growth of audio databases, many music retrieval applications have employed metadata descriptions to facilitate better handling of huge databases. Music structure creates the uniqueness identity for each music piece. Therefore, structural description is capable of providing a powerful way of interacting with audio content, and serves as a linkage between low-level description and higher-level descriptions of audio (e.g. audio summarization, audio fingerprinting, etc.). Identification of representative musical excerpts is the primary step towards the goal of generating structural descriptions of audio signals. In this paper, we will provide a systematic review of the existing work on extracting musical structure descriptors from music files and will present, discuss, and evaluate various approaches in identifying representative musical excerpts of music audio signals.