Samir Sadok

15 papers A 1Misc 1Journal 10Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Residual Tokens Enhance Masked Autoencoders for Speech Modeling.
CoRR
Samir Sadok, Stéphane Lathuilière, Xavier Alameda-Pineda
2026 J jnl
The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs.
CoRR
Samir Sadok, Laurent Girin, Xavier Alameda-Pineda
2025 J jnl
A vector quantized masked autoencoder for audiovisual speech emotion recognition.
Comput. Vis. Image Underst.
Samir Sadok, Simon Leglaive, Renaud Séguier
2025 Misc conf
AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder.
ICASSP
Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda
2025 J jnl
AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder.
CoRR
Samir Sadok, Simon Leglaive, Laurent Girin, Gaël Richard, Xavier Alameda-Pineda
2025 A conf
Bringing Interpretability to Neural Audio Codecs.
INTERSPEECH
Samir Sadok, Julien Hauret, Éric Bavu
2024 J jnl
A multimodal dynamical variational autoencoder for audiovisual speech representation learning.
Neural Networks
Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier
2024 — —
Audiovisual speech representation learning applied to emotion recognition. (Apprentissage de représentation de la parole audiovisuelle pour la reconnaissance des émotions).
Samir Sadok
2024 — conf
Can AI Decode the Circumplex Model of Affect? A Data-driven Study.
ICPR (Workshops and Challenges, 1)
Amdjed Belaref, Samir Sadok, Karim M. Ibrahim, Zineb Noumir, Renaud Séguier
2023 J jnl
A Multimodal Dynamical Variational Autoencoder for Audiovisual Speech Representation Learning.
CoRR
Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier
2023 — conf
A Vector Quantized Masked Autoencoder for Speech Emotion Recognition.
ICASSP Workshops
Samir Sadok, Simon Leglaive, Renaud Séguier
2023 J jnl
A vector quantized masked autoencoder for audiovisual speech emotion recognition.
CoRR
Samir Sadok, Simon Leglaive, Renaud Séguier
2023 J jnl
A vector quantized masked autoencoder for speech emotion recognition.
CoRR
Samir Sadok, Simon Leglaive, Renaud Séguier
2023 J jnl
Learning and controlling the source-filter representation of speech with a variational autoencoder.
Speech Commun.
Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier
2022 J jnl
Learning and controlling the source-filter representation of speech with a variational autoencoder.
CoRR
Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier