Sketch2Sound Adobe

Sketch2Sound Adobe is a generative audio model designed for sound artists and designers who need to create high-quality sounds from a set of interpretable time-varying control signals and text prompts.
The model works by applying random median filters to the control signals during training, allowing it to be prompted using controls with flexible levels of temporal specificity. This enables Sketch2Sound to synthesize sounds that follow the gist of input controls from a vocal imitation while retaining adherence to an input text prompt and audio quality.
Sound artists and designers who need to create sounds with the semantic flexibility of text prompts and the expressivity and precision of a sonic gesture or vocal imitation will get the most value from Sketch2Sound Adobe, as it allows them to create sounds that are synced to video through vocal imitations and retain high audio quality.