Publications
Decode, move and speak!Self-supervised learning of speech units, gestures and sounds relationships using vocal imitation.→Articulatory-Regularized Variational AutoEncoderLearning robust speech representation with an articulatory-regularized variational autoencoder.→Imitative speech modelSelf-supervised learning of acoustic-to-articulatory mapping by vocal imitation.→Towards an articulatory-driven neural vocoderPreliminary speech synthesis results presented at ISSP 2020.→