Data-Driven Room Acoustic Modeling Via Differentiable Feedback Delay Networks With Learnable Delay Lines
This addresses the problem of automating reverberation algorithm tuning for audio engineers and researchers, representing a novel method for a known bottleneck rather than an incremental improvement.
The paper tackles the challenge of automatic parameter tuning for Feedback Delay Networks (FDNs) in room acoustic modeling by introducing a differentiable FDN with trainable delay lines, enabling simultaneous learning of all parameters via backpropagation. The method outperforms existing approaches like genetic algorithms and analytical design in matching target acoustical characteristics.
Over the past few decades, extensive research has been devoted to the design of artificial reverberation algorithms aimed at emulating the room acoustics of physical environments. Despite significant advancements, automatic parameter tuning of delay-network models remains an open challenge. We introduce a novel method for finding the parameters of a Feedback Delay Network (FDN) such that its output renders target attributes of a measured room impulse response. The proposed approach involves the implementation of a differentiable FDN with trainable delay lines, which, for the first time, allows us to simultaneously learn each and every delay-network parameter via backpropagation. The iterative optimization process seeks to minimize a perceptually-motivated time-domain loss function incorporating differentiable terms accounting for energy decay and echo density. Through experimental validation, we show that the proposed method yields time-invariant frequency-independent FDNs capable of closely matching the desired acoustical characteristics, and outperforms existing methods based on genetic algorithms and analytical FDN design.