Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
publications
Learning and controlling the source-filter representation of speech with a variational autoencoder
Published in Speech Communication, 2023
We show that the source-filter model of speech production naturally emerges in the latent space of an unsupervised VAE and we propose a weakly-supervised method to control the pitch and formant frequencies of speech signals in the VAE latent space.
Recommended citation: Learning and controlling the source-filter representation of speech with a variational autoencoder Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier Speech Communication, vol. 148, 2023. https://www-sciencedirect-com.ezproxy.universite-paris-saclay.fr/science/article/pii/S0167639323000304
A vector quantized masked autoencoder for speech emotion recognition
Published in Workshop ICASSP (SASB), 2023
Combined VQ-VAE (unsupervised) with MAE (self-supervised) for speech emotion recognition.
Recommended citation: Sadok Samir, Simon Leglaive and Renaud Séguier. “A vector quantized masked autoencoder for speech emotion recognition.” (2023). ☍
A multimodal dynamical variational autoencoder for audiovisual speech representation learning
Published in Neural Networks (Elsevier), 2024
We present a multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning.
Recommended citation: Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier. A multimodal dynamical variational autoencoder for audiovisual speech representation learning. Neural Networks (Elsevier), 2024 (link)
AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder
Published in IEEE ICASSP, 2025
We present AnCoGen, a new method using a masked autoencoder to unify speech signal analysis, control, and generation in single model.
Recommended citation: Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda. AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder. IEEE ICASSP, 2025 ☍
talks
Apprentissage des représentations de la parole et du langage
Published:
The objective of this day is to bring together researchers from the written, oral and sign language processing communities to study the representations extracted by deep neural models from massive data.
CFA: French Congress for Acoustics
Published:
Presentation on my work: learning and control of variation factors for speech with variational autoencoders
Méthodes en traitement du signal pour l’écoute artificielle
Published:
Methods and models in signal processing.
teaching
Practical work
Workshop, University de Rennes 1, 2021
I was supervising students during their practical work:
Project supervision
Workshop, CentralesSupelec, 2022
Supervision of two student projects for machine learning and deep learning.