Quartz 5
Search
Search
Dark mode
Light mode
Explorer
Home
❯
sources
sources
11 items under this folder.
Jun 30, 2026
Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra
speech-parameterization
speech-synthesis
generative-models
rbm
complex-valued-neural-networks
ieee-taslp
Jun 29, 2026
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks
deep-learning
uncertainty-quantification
heteroscedastic-regression
iclr
Jun 29, 2026
Hyperspherical Variational Auto-Encoders
deep-learning
variational-autoencoder
hyperspherical-latent-space
directional-statistics
uai
Jun 29, 2026
Poisson Variational Autoencoder
deep-learning
variational-autoencoder
discrete-latent-variable
computational-neuroscience
neurips
Jun 28, 2026
ComplexOrlicz: Holomorphic Gradient Orthogonalization for Tail-Adaptive Uncertainty Beyond Gaussian Limits
deep-learning
uncertainty-quantification
heteroscedastic-regression
complex-valued-modeling
withdrawn-preprint
Jun 28, 2026
EuleroDec: A Complex-Valued RVQ-VAE for Efficient and Robust Audio Coding
audio-coding
complex-valued-neural-networks
vq-vae
speech-processing
Jun 28, 2026
Faithful Heteroscedastic Regression with Neural Networks
deep-learning
uncertainty-quantification
heteroscedastic-regression
calibration
aistats
Jun 28, 2026
Gamma-VAE: Speech representation based on VAE assuming gamma distribution for both latent variables and observation
speech-processing
variational-autoencoder
gamma-distribution
generative-models
Jun 28, 2026
A Power-Weighted Noncentral Complex Gaussian Distribution
statistics
signal-processing
complex-valued-modeling
speech-processing
Jun 28, 2026
Building Blocks for a Complex-Valued Transformer Architecture
deep-learning
transformer
complex-valued-neural-networks
signal-processing
Jun 28, 2026
Complex-Valued Variational Autoencoder: A Novel Deep Generative Model for Direct Representation of Complex Spectra
speech-processing
variational-autoencoder
complex-valued-neural-networks
generative-models
interspeech