Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A post-processing procedure for improving music tempo estimates using supervised learning

: Schreiber, H.; Müller, M.

International Society for Music Information Retrieval -ISMIR-:
18th International Society for Music Information Retrieval Conference, ISMIR 2017. Proceedings : 23rd - 27th October 2017, Suzhou, China
Suzhou, 2017
ISBN: 978-9-8111517-9-8
International Society for Music Information Retrieval (ISMIR Conference) <18, 2017, Suzhou>
Conference Paper
Fraunhofer IIS ()

Tempo estimation is a fundamental problem in music information retrieval and has been researched extensively. One problem still unsolved is the tendency of tempo estimation algorithms to produce results that are wrong by a small number of known factors (so-called octave errors). We propose a method that uses supervised learning to predict such tempo estimation errors. In a post-processing step, these predictions can then be used to correct an algorithm's tempo estimates. While being simple and relying only on a small number of features, our proposed method significantly increases accuracy for state-of-the-art tempo estimation methods.