Return to Members

Xiaoyu Bie

I’m currently a Ph.D. student in the Perception team at INRIA since November 2019. I received my B.Sc. degree in Optical & Electronic Information from Huazhong University of Science & Technology, China, in 2016, the diplôme d’ingénieur from Institut d’Optique Graduate School, France, in 2018 and the M.Sc. in Signal & Image Processing from University Paris-Saclay, France, in 2018. My research interests are broadly in deep generative models and audio-visual applications.


Publications (Google Scholar)

  • Xiaoyu Bie, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, “Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders”. arXiv preprint arXiv:2106.12271 [pdf]
  • Xiaoyu Bie, Laurent Girin, Simon Leglaive, Thomas Hueber, Xavier Alameda-Pineda, “A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling”. Interspeech 2021. [pdf]
  • Wen Guo, Xiaoyu Bie, Xavier Alameda-Pineda, Francesc Moreno, “Multi-Person Extreme Motion Prediction with Cross-Interaction Attention”. arXiv preprint arXiv:2105.08825. [pdf] [project]
  • Laurent Girin, Simon Leglaive, Xiaoyu Bie, Julien Diard, Thomas Hueber, Xavier Alameda-Pineda. “Dynamical Variational Autoencoders: A Comprehensive Review”. arXiv preprint arXiv:2008.12595, 2020. [pdf]




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