Sound effects model design commonly uses digital signal processing techniques with full control ability, but it is difficult to achieve realism within a limited number of parameters. Recently, neural sound effects synthesis methods have emerged as a promising approach for generating high-quality and realistic sounds, but the process of synthesizing the desired sound poses difficulties in terms of control. This paper presents a real-time neural synthesis model guided by a physically inspired model, enabling the generation of high-quality sounds while inheriting the control interface of the physically inspired model. We showcase the superior performance of our model in terms of sound quality and control.
View on arXiv@article{zong2025_2503.08806,
title={ Learning Control of Neural Sound Effects Synthesis from Physically Inspired Models },
author={ Yisu Zong and Joshua Reiss },
journal={arXiv preprint arXiv:2503.08806},
year={ 2025 }
}