no code implementations • 7 Nov 2023 • Shahan Nercessian, Johannes Imort
We introduce the text-to-instrument task, which aims at generating sample-based musical instruments based on textual prompts.
no code implementations • 15 Aug 2022 • Shahan Nercessian
In this paper, we propose a differentiable WORLD synthesizer and demonstrate its use in end-to-end audio style transfer tasks such as (singing) voice conversion and the DDSP timbre transfer task.
no code implementations • 15 Mar 2021 • Shahan Nercessian, Andy Sarroff, Kurt James Werner
In this work, we propose using differentiable cascaded biquads to model an audio distortion effect.