5 papers
Rethinking Magnitude Compression in Spectral Losses for DDSP Parameter Estimation
Byunghoo Park, Jayeon Yi, Minje Kim
Spectral losses for differentiable digital signal processing (DDSP) commonly compress magnitudes, for example by using log-magnitude terms. Such compression mimics human perception…
Accurate Plate Reverb Parameter Estimation Using Two-Stage Evolutionary Search
Byunghoo Park, Jayeon Yi, Takyoung Kim +1
We describe our submission to Task A of the 1st DAFx parameter estimation challenge. The task is to recover the six physical parameters of a simulated metal-plate reverberator -- i…
From Hallucination to Articulation: Language Model-Driven Losses for Ultra Low-Bitrate Neural Speech Coding
Jayeon Yi, Minje Kim
``Phoneme Hallucinations (PH)'' commonly occur in low-bitrate DNN-based codecs. It is the generative decoder's attempt to synthesize plausible outputs from excessively compressed t…
DDD: A Perceptually Superior Low-Response-Time DNN-based Declipper
Jayeon Yi, Junghyun Koo, Kyogu Lee
Clipping is a common nonlinear distortion that occurs whenever the input or output of an audio system exceeds the supported range. This phenomenon undermines not only the perceptio…
Beat-Aligned Spectrogram-to-Sequence Generation of Rhythm-Game Charts
Jayeon Yi, Sungho Lee, Kyogu Lee
In the heart of "rhythm games" - games where players must perform actions in sync with a piece of music - are "charts", the directives to be given to players. We newly formulate ch…