InstrumentGen: Generating Sample-Based Musical Instruments From Text
This work addresses the challenge of automatic sample-based instrument generation for music production and AI applications, representing an incremental step by extending existing text-prompted generative audio frameworks.
The paper tackles the problem of generating sample-based musical instruments from textual prompts, introducing the text-to-instrument task and proposing InstrumentGen, a model that conditions on various attributes like instrument family and pitch, with results establishing a foundational baseline for this domain.
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.