This paper describes a machine learning approach to the problem of identifying professional musicians from their playing style. We focus on the identification of jazz saxophonists by studying how they express and communicate their view of the musical and emotional content of musical pieces (performed from a musical score). In particular, we investigate expressive deviations of parameters such as pitch, timing, amplitude and timbre in monophonic audio recordings. We describe how we extract a symbolic description from the audio recordings and how we use this symbolic description to train a performance-based interpreter classifier.
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.