Výsledky vyhledávání - "Diard, Julien"

Report

Repeat after me: Self-supervised learning of acoustic-to-articulatory mapping by vocal imitation

Autor: Georges, Marc-Antoine, Diard, Julien, Girin, Laurent, Schwartz, Jean-Luc, Hueber, Thomas

We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward model pre

Externí odkaz: http://arxiv.org/abs/2204.02269

Zobrazit plný text záznamu

Report

Dynamical Variational Autoencoders: A Comprehensive Review

Autor: Girin, Laurent, Leglaive, Simon, Bie, Xiaoyu, Diard, Julien, Hueber, Thomas, Alameda-Pineda, Xavier

Publikováno v: Foundations and Trends in Machine Learning, Vol. 15, No. 1-2, pp 1-175, 2021

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data vectors are

Externí odkaz: http://arxiv.org/abs/2008.12595

Zobrazit plný text záznamu