Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Automatic best take detection for electric guitar and vocal studio recordings

: Bönsel, Carsten; Abeßer, Jakob; Grollmisch, Sascha; Mimilakis, Stylianos-Ioannis

Volltext (PDF; )

Man, B. de ; Audio Engineering Society -AES-:
2nd Workshop on Intelligent Music Production 2016. Proceedings. Online resource : 13 September 2016, London
London, 2016
2 S.
Workshop on Intelligent Music Production <2, 2016, London>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IDMT ()

In the course of music recording sessions, the same vocal or instrumental passages are usually performed several times. However, only the best takes are chosen and further processed. Especially for lead vocals and solo instruments, the quantity of recorded material can be overwhelming, which makes the selection process time-consuming. Our goal is to automate and objectify this procedure in order to assist music producers for a faster decision making. The task of automatic best take detection is constrained to monophonic lines of electric guitar and singing voice in popular music. Assuming realistic scenarios during recording sessions, the proposed system requires only a synchronized click track and a backing track with accompanying instruments to be available for analysis.