activity
20182023
most citedA variance modeling framework based on variational autoencoders for speech enhancement

59 citations · 147 across the 14 of their papers we have counts for

collaborators

25 papers

eess.AS2023

Unsupervised speech enhancement with deep dynamical generative speech and noise models

Xiaoyu Lin, Simon Leglaive, Laurent Girin +1

This work builds on a previous work on unsupervised speech enhancement using a dynamical variational autoencoder (DVAE) as the clean speech model and non-negative matrix factorizat…

cs.SD2022

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

Marc-Antoine Georges, Julien Diard, Laurent Girin +2

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 interpr…

cs.CV20227 cited

HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE

Xiaoyu Bie, Wen Guo, Simon Leglaive +3

Studies on the automatic processing of 3D human pose data have flourished in the recent past. In this paper, we are interested in the generation of plausible and diverse future hum…

cs.LG2022

Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencoder

Xiaoyu Lin, Laurent Girin, Xavier Alameda-Pineda

In this paper, we present an unsupervised probabilistic model and associated estimation algorithm for multi-object tracking (MOT) based on a dynamical variational autoencoder (DVAE…

cs.SD2021

SALADnet: Self-Attentive multisource Localization in the Ambisonics Domain

Pierre-Amaury Grumiaux, Srdan Kitic, Prerak Srivastava +2

In this work, we propose a novel self-attention based neural network for robust multi-speaker localization from Ambisonics recordings. Starting from a state-of-the-art convolutiona…

cs.SD2021

A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling

Xiaoyu Bie, Laurent Girin, Simon Leglaive +2

The Variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space lea…