10 papers
Accelerating Automatic Differentiation of Direct Form Digital Filters
Chin-Yun Yu, György Fazekas
We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The…
Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior
Chin-Yun Yu, Marco A. MartÃnez-RamÃrez, Junghyun Koo +3
Style Transfer with Inference-Time Optimisation (ST-ITO) is a recent approach for transferring the applied effects of a reference audio to an audio track. It optimises the effect p…
Sound Matching an Analogue Levelling Amplifier Using the Newton-Raphson Method
Chin-Yun Yu, György Fazekas
Automatic differentiation through digital signal processing algorithms for virtual analogue modelling has recently gained popularity. These algorithms are typically more computatio…
DiffVox: A Differentiable Model for Capturing and Analysing Vocal Effects Distributions
Chin-Yun Yu, Marco A. MartÃnez-RamÃrez, Junghyun Koo +4
This study introduces a novel and interpretable model, DiffVox, for matching vocal effects in music production. DiffVox, short for ``Differentiable Vocal Fx", integrates parametric…
Time-of-arrival Estimation and Phase Unwrapping of Head-related Transfer Functions With Integer Linear Programming
Chin-Yun Yu, Johan Pauwels, György Fazekas
In binaural audio synthesis, aligning head-related impulse responses (HRIRs) in time has been an important pre-processing step, enabling accurate spatial interpolation and efficien…
Zero-Shot Duet Singing Voices Separation with Diffusion Models
Chin-Yun Yu, Emilian Postolache, Emanuele Rodolà +1
In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target sig…