About me

Recently holding a doctorate, entitled “Audiovisual speech representation learning applied to emotion recognition”, I am embarking on a new journey in a post-doctoral position.

My research spans multimodal (audiovisual) and generative models. I aim to develop latent spaces that encode high-level features in an interpretable manner, facilitating human understanding.

News

• Thesis defense 🎉 : (08-03-2024)
• Article accepted 🎉 : (09-01-2024) ‘A multimodal dynamical variational autoencoder for audiovisual speech representation learning’ is accepted for Neural networks, 2024.
• Article accepted 🎉 : (14-04-2023) ‘A vector quantized masked autoencoder for speech emotion recognition’ is accepted for the workshop Self-supervision in Audio, Speech and Beyond, ICASSP SASB 2023.
• Article accepted 🎉 : (14-04-2023) ‘learning and controlling the source-filter representation of speech with a variational autoencoder’ has been accepted for Speech Communication publication.