Music Information Retrieval with Temporal Features and Timbre

At a time when the quantity of music media surrounding us is rapidly increasing and the access to recordings as well as the amount of music files available on the Internet is constantly growing, the problem of building music recommendation systems is of great importance. In this work, we perform a study on automatic classification of musical instruments. We use monophonic sounds. The latter have successfully been classified in the past, with main focus on pitch. We propose new temporal features and incorporate timbre descriptors. The advantages of this approach are: preservation of temporal information and high classification accuracy.