Dynamics are one of the fundamental tools of expressivity in a performance.
While the usage of this tool is highly subjective, a systematic methodology
to derive loudness markings based on a performance can be highly beneficial.
With this goal in mind, this paper is a first step towards developing a methodology
to automatically transcribe dynamic markings from vocal rock and pop performances.
To this end, we make use of commercial recordings of some popular
songs followed by source separation ...
Dynamics are one of the fundamental tools of expressivity in a performance.
While the usage of this tool is highly subjective, a systematic methodology
to derive loudness markings based on a performance can be highly beneficial.
With this goal in mind, this paper is a first step towards developing a methodology
to automatically transcribe dynamic markings from vocal rock and pop performances.
To this end, we make use of commercial recordings of some popular
songs followed by source separation and compare them to the karaoke versions
of the same songs. The dynamic variations in the original commercial recordings
are found to be structurally very similar to the aligned karaoke/multi-track versions
of the same tracks. We compare and show the differences between tracks
using statistical analysis, with an eventual goal to use the transcribed markings
as guiding tools, to help students adapt with a specific interpretation of a given
piece of music. We perform a qualitative analysis of the proposed methodology
with the teachers in terms of informativeness and accuracy.
+