arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.08060eess.AScs.SD

DDSP-SFX:基于可微分数字信号处理的声学引导音效生成

DDSP-SFX: Acoustically-guided sound effects generation with differentiable digital signal processing

Dolby Laboratory(杜比实验室)

Yunyi Liu, Craig Jin, David Gunawan

AI总结:

本文提出DDSP-SFX模型,基于可微分数字信号处理实现高质量音效合成,并通过瞬态建模与音色控制方法支持确定性的声学属性控制和音色迁移。

摘要:

使用神经音频合成模型控制音效变化一直是一项困难的任务。可微分数字信号处理(DDSP)提供了一种轻量级解决方案,通过结合预处理音频特征和数字合成器,在实现高质量声音合成的同时支持确定性的声学属性控制。在本研究中,我们提出了DDSP-SFX,这是一个基于DDSP架构的模型,能够合成高质量音效,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和主观评分。我们提出了一种简单的方法,在实现音色变化控制的同时也支持确定性属性控制。我们进一步以语音作为引导声音,定性地展示了音色迁移性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑