DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.
Ddsp: Differentiable digital signal processing
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
DART adds differentiability to acoustic radiance transfer, enabling material optimization and improved performance on sparse acoustic field prediction tasks compared to signal processing and neural baselines.
Multi-token prediction accounts for nearly all rollout stability gains on synthetic three-component seismograms, with sharp dependence on context covering the full P-S interval and magnitude-based losses unable to prevent polarity flips.
Explicit noise modeling during differentiable optimization improves attenuation filter accuracy in feedback delay networks when room impulse responses are noisy.
witheFlow continuously maps a live performer's physiological state and audio valence-arousal onto the gains of DAW effect channels via interpretable YAML rules.
citing papers explorer
-
DiffWave: A Versatile Diffusion Model for Audio Synthesis
DiffWave is a non-autoregressive diffusion model that generates high-fidelity audio waveforms from noise in constant steps, matching WaveNet vocoder quality while being orders of magnitude faster and outperforming prior models in unconditional generation.
-
Differentiable Acoustic Radiance Transfer
DART adds differentiability to acoustic radiance transfer, enabling material optimization and improved performance on sparse acoustic field prediction tasks compared to signal processing and neural baselines.
-
When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms
Multi-token prediction accounts for nearly all rollout stability gains on synthetic three-component seismograms, with sharp dependence on context covering the full P-S interval and magnitude-based losses unable to prevent polarity flips.
-
Learning Filters in Feedback Delay Networks from Noisy Room Impulse Responses
Explicit noise modeling during differentiable optimization improves attenuation filter accuracy in feedback delay networks when room impulse responses are noisy.
-
Go witheFlow: Real-time Emotion Driven Audio Effects Modulation
witheFlow continuously maps a live performer's physiological state and audio valence-arousal onto the gains of DAW effect channels via interpretable YAML rules.