arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.07970eess.AScs.LGcs.SD
收藏

用于时变音频系统的可微全极点滤波器

Differentiable All-pole Filters for Time-varying Audio Systems

Chin-Yun Yu Equal contribution. ,\, Christopher Mitcheltree ,\, Alistair Carson ,\, Stefan Bilbao ,\, Joshua D. Reiss ,\

Chin-Yun Yu, Christopher Mitcheltree, Alistair Carson, Stefan Bilbao, Joshua D. Reiss, György Fazekas

AI总结:

本文提出一种可微时变全极点滤波器实现,使递归滤波器梯度能通过自身反向传播,从而突破自动微分框架限制,实现含极点滤波器的音频系统端到端训练,并在移相器、合成器和压缩器上验证了其训练效率与建模能力。

摘要:

无限脉冲响应滤波器是许多时变音频系统(如音频效果器和合成器)的基本构建模块。然而,其递归结构阻碍了使用自动微分对这些系统进行端到端训练。尽管频率采样和基于帧的处理等非递归滤波器近似方法已在先前工作中被提出并广泛使用,但它们无法准确反映原始系统的梯度。我们通过重新表达时变全极点滤波器,使其梯度能够通过自身反向传播,从而缓解了这一困难,因此滤波器实现不再受自动微分框架技术限制的约束。该实现可用于包含带极点滤波器的音频系统中,以实现高效的梯度评估。我们在移相器、时变减法合成器和压缩器上展示了其在建模真实世界动态音频系统方面的训练效率和表达能力。我们公开了代码和音频样本,并在 VST 插件中提供了训练好的音频效果器和合成器模型,网址为 https://diffapf.github.io/web/。

英文摘要:

Infinite impulse response filters are an essential building block of many time-varying audio systems, such as audio effects and synthesisers. However, their recursive structure impedes end-to-end training of these systems using automatic differentiation. Although non-recursive filter approximations like frequency sampling and frame-based processing have been proposed and widely used in previous works, they cannot accurately reflect the gradient of the original system. We alleviate this difficulty by re-expressing a time-varying all-pole filter to backpropagate the gradients through itself, so the filter implementation is not bound to the technical limitations of automatic differentiation frameworks. This implementation can be employed within audio systems containing filters with poles for efficient gradient evaluation. We demonstrate its training efficiency and expressive capabilities for modelling real-world dynamic audio systems on a phaser, time-varying subtractive synthesiser, and compressor. We make our code and audio samples available and provide the trained audio effect and synth models in a VST plugin at https://diffapf.github.io/web/.

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。

↑