Publications

2026

  1. Variational Encoder–Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition
    Anderson Augusma, Dominique Vaufreydaz , and Frédérique Letué
    In , Apr 2026
    working paper or preprint
    PDF
  2. Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction
    Adrien Schneider , Kacper Zabkowski , Anderson Augusma, and 3 more authors
    In 6th Symposium on Security and Privacy in Speech Communication joined with 4th Voice Privacy Challenge at Interspeech 2026 , Jul 2026
    PDF

2024

  1. Exploring VQ-VAE with Prosody Parameters for Speaker Anonymization
    Sotheara Leang , Anderson Augusma, Eric Castelli , and 3 more authors
    In Voice Privacy Challenge 2024 at INTERSPEECH 2024 , Sep 2024
    PDF

2023

  1. Multimodal Group Emotion Recognition In-the-wild Using Privacy-Compliant Features
    Anderson Augusma, Dominique Vaufreydaz , and Frédérique Letué
    In ICMI ’23: International Conference on Multimodal Interaction , Oct 2023
    PDF

2022

  1. Multimodal Perception and Statistical Modeling of Pedagogical Classroom Events Using a Privacy-safe Non-individual Approach
    Anderson Augusma
    In Doctoral Consortium of 10th International Conference on Affective Computing & Intelligent Interaction (ACII 2022) , Oct 2022
    PDF