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.
https://www.aes.org/e-lib/browse.cfm?elib=17104
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.
Learn more about the AES E-Library
Start a discussion about this paper!