Controlling the variations of sound effects using neural audio synthesis models has been a difficult task. Differentiable digital signal processing (DDSP) provides a lightweight solution that achieves high-quality sound synthesis while enabling deterministic acoustic attribute control by incorporating pre-processed audio features and digital synthesizers. In this research, we introduce DDSP-SFX, a model based on the DDSP architecture capable of synthesizing high-quality sound effects while enabling users to control the timbre variations easily. We propose a transient modelling technique with higher objective evaluation scores and subjective ratings over impulsive signals (footsteps, gunshots). We propose a simple method that achieves timbre variation control while also allowing deterministic attribute control. We further qualitatively show the timbre transfer performance using voice as the guiding sound.

翻译：利用神经音频合成模型控制音效变化一直是一项艰巨的任务。可微数字信号处理通过整合预处理音频特征与数字合成器，提供了一种轻量级解决方案，既能实现高质量声音合成，又能支持确定性声学属性控制。本研究提出DDSP-SFX模型，该模型基于DDSP架构，可合成高质量音效，同时使用户能够轻松控制音色变化。我们提出了一种瞬态建模技术，在脉冲信号（脚步声、枪声）上获得了更高的客观评估分数与主观评价。我们提出了一种简单方法，既能实现音色变化控制，又能进行确定性属性控制。我们进一步通过语音作为引导声音，定性展示了音色迁移性能。