Xiaoyu Lin

I am a Postdoc fellow at Robotlearn team from July 2024 to December 2024.

Previously, I was a PhD student in the Perception/Robotlearn team from November 1st 2020 to June 2024.
I defended my PhD thesis on June 26th 2024.

Contact

  • INRIA Grenoble Rhone-Alpes
    655, avenue de l’Europe
    38330 Montbonnot Saint-Martin
    France
  • Email: xiaoyu dot lin at inria dot fr

Publications

Publications HAL de Xiaoyu Lin

2024

Journal articles

titre
Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation
auteur
Xiaoyu Lin, Laurent Girin, Xavier Alameda-Pineda
article
Transactions on Machine Learning Research Journal, 2024, pp.1-19
Accès au texte intégral et bibtex
https://inria.hal.science/hal-03584014/file/2202.09315.pdf BibTex

Theses

titre
Deep latent-variable generative models for multimedia processing
auteur
Xiaoyu Lin
article
Machine Learning [cs.LG]. Université Grenoble Alpes [2020-..], 2024. English. ⟨NNT : 2024GRALM027⟩
Accès au texte intégral et bibtex
https://theses.hal.science/tel-04957490/file/LIN_2024_archivage.pdf BibTex

2023

Conference papers

titre
Unsupervised speech enhancement with deep dynamical generative speech and noise models
auteur
Xiaoyu Lin, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda
article
Interspeech 2023 – 24th Annual Conference of the International Speech Communication Association, ISCA, Aug 2023, Dublin, Ireland. pp.1-5
Accès au bibtex
https://arxiv.org/pdf/2306.07820 BibTex
titre
Speech Modeling with a Hierarchical Transformer Dynamical VAE
auteur
Xiaoyu Lin, Xiaoyu Bie, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda
article
ICASSP 2023 – IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2023, Rhodes, Greece. pp.1-5, ⟨10.1109/ICASSP49357.2023.10096751⟩
Accès au bibtex
https://arxiv.org/pdf/2303.09404 BibTex