Differentiable Artificial Reverberation
- 22 July 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 30 (23299290) , 2541-2556
Abstract
Artificial reverberation (AR) models play a central role in various audio applications. Therefore, estimating the AR model parameters (ARPs) of a reference reverberation is a crucial task. Although a few recent deep-learning-based approaches have shown promising performance, their non-end-to-end training scheme prevents them from fully exploiting the potential of deep neural networks. This motivates the introduction of differentiable artificial reverberation (DAR) models, allowing loss gradients to be back-propagated end-to-end. However, implementing the AR models with their difference equations “as is” in the deep learning framework severely bottlenecks the training speed when executed with a parallel processor like GPU due to their infinite impulse response (IIR) components. We tackle this problem by replacing the IIR filters with finite impulse response (FIR) approximations with the frequency-sampling method. Using this technique, we implement three DAR models—differentiable Filtered Velvet Noise (FVN), Advanced Filtered Velvet Noise (AFVN), and Delay Network (DN). For each AR model, we train its ARP estimation networks for analysis-synthesis (RIR-to-ARP) and blind estimation (reverberant-speech-to-ARP) task in an end-to-end manner with its DAR model counterpart. Experiment results show that the proposed method achieves consistent performance improvement over the non-end-to-end approaches in both objective metrics and subjective listening test results.Keywords
All Related Versions
Funding Information
- Institute of Information & Communications Technology Planning & Evaluation
- Korean government (2022-0-00641, NRF-2018M3A7B4089670)
- National Research Foundation of Korea
This publication has 36 references indexed in Scilit:
- Measuring Room Impulse Responses: Impact of the Decay Range on Derived Room Acoustic ParametersActa Acustica united with Acustica, 2012
- The just noticeable difference of center time and clarity index in large reverberant spacesThe Journal of the Acoustical Society of America, 2010
- On the minimum audible difference in direct-to-reverberant energy ratioThe Journal of the Acoustical Society of America, 2008
- Circulant and elliptic feedback delay networks for artificial reverberationIEEE Transactions on Speech and Audio Processing, 1997
- An adaptive backpropagation cascade IIR filterIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 1992
- FIR and IIR Synapses, a New Neural Network Architecture for Time Series ModelingNeural Computation, 1991
- Spectral Modeling Synthesis: A Sound Analysis/Synthesis System Based on a Deterministic Plus Stochastic DecompositionComputer Music Journal, 1990
- Identification of systems containing linear dynamic and static nonlinear elementsAutomatica, 1982
- An approach to the approximation problem for nonrecursive digital filtersIEEE Transactions on Audio and Electroacoustics, 1970
- "Colorless" artificial reverberationIRE Transactions on Audio, 1961