EXPLORING APPROACHES TO MULTI-TASK AUTOMATIC SYNTHESIZER PROGRAMMING

Daniel Faronbi (NYU) joins us to talk about his recent ICASSP paper

Automatic Synthesizer Programming is the task of transform-
ing an audio signal that was generated from a virtual instru-
ment, into the parameters of a sound synthesizer that would
generate this signal. In the past, this could only be done for
one virtual instrument. In this paper, we expand the current
literature by exploring approaches to automatic synthesizer
programming for multiple virtual instruments. Two different
approaches to multi-task automatic synthesizer programming
are presented. We find that the joint-decoder approach per-
forms best. We also evaluate the performance of this model
for different timbre instruments and different latent dimension
sizes.

NOTE: this event is part of the DL4MIR workshop series (ccrma-mir.github.io); guest speaker talks are open to the broader CCRMA community.