38 citations · 58 across the 3 of their papers we have counts for
3 papers
cs.SD2023★ 3 cited
From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
Robin San Roman, Yossi Adi, Antoine Deleforge +3
Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recent…
cs.LG2021★ 17 cited
Non Gaussian Denoising Diffusion Models
Eliya Nachmani, Robin San Roman, Lior Wolf
Generative diffusion processes are an emerging and effective tool for image and speech generation. In the existing methods, the underline noise distribution of the diffusion proces…
cs.LG2021★ 38 cited
Noise Estimation for Generative Diffusion Models
Robin San-Roman, Eliya Nachmani, Lior Wolf
Generative diffusion models have emerged as leading models in speech and image generation. However, in order to perform well with a small number of denoising steps, a costly tuning…