Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Instrument-centered music transcription of bass guitar tracks

: Abeßer, J.; Schuller, G.

Dittmar, C. ; Audio Engineering Society -AES-:
53rd International Conference on Semantic Audio 2014 : London, United Kingdom 26 – 29 January 2014
Red Hook, NY: Curran, 2014
ISBN: 978-1-63266-284-2
ISBN: 1-63266-284-1
International Conference on Semantic Audio <53, 2014, London>
Conference Paper
Fraunhofer IDMT ()

In this paper, we propose an instrument-centered bass guitar transcription algorithm. Instead of aiming at a general-purpose bass transcription algorithm, we incorporate knowledge about the instrument construction and typical playing techniques of the electric bass guitar. In addition to the commonly extracted score-level parameters note onset, offset, and pitch, we also estimate the additional instrument-level note parameters string number, fret number, plucking style, and expression style. The proposed algorithm achieved an F-measure value of 0.901 for the note-wise transcription evaluation on a novel evaluation dataset and outperformed three state-of-the-art bass transcription algorithms.