Proceedings of the 53rd AES Conference on Semantic Audio, Audio Engineering Society
Original Kurzfassung:
We present a first integrated prototype towards our long-term goal of building a complete classical music
companion. When listening to a live performance of classical piano music, our system is able to almost
instantly identify the piece that is being played, and the position within the piece. It then tracks the
performance via an accurate and robust score following algorithm and shows the sheet music accordingly.
Furthermore, the system continuously re-evaluates its current position hypotheses within a database of scores
(roughly 1,000,000 notes!) and is capable of detecting arbitrary 'jumps' by the performer (e.g., leaving out
repetitions, re-starts at any position, etc.) - not only within a piece, but within the complete database of
classical piano scores.
Forschungs-