InstrumentGen: Generating Sample-Based Musical Instruments From Text
Author:
Shahan Nercessian, Johannes Imort
Keyword:
Electrical Engineering and Systems Science, Audio and Speech Processing, Audio and Speech Processing (eess.AS), Machine Learning (cs.LG), Sound (cs.SD)
journal:
--
date:
2023-11-06 16:00:00
Abstract
We introduce the text-to-instrument task, which aims at generating sample-based musical instruments based on textual prompts. Accordingly, we propose InstrumentGen, a model that extends a text-prompted generative audio framework to condition on instrument family, source type, pitch (across an 88-key spectrum), velocity, and a joint text/audio embedding. Furthermore, we present a differentiable loss function to evaluate the intra-instrument timbral consistency of sample-based instruments. Our results establish a foundational text-to-instrument baseline, extending research in the domain of automatic sample-based instrument generation.