Search Results for author:
Found 7 papers, 0 papers with code
Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE
The human perception system is often assumed to recruit motor knowledge when processing auditory speech inputs.
Repeat after me: Self-supervised learning of acoustic-to-articulatory mapping by vocal imitation
We propose a computational model of speech production combining a pre-trained neural articulatory synthesizer able to reproduce complex speech stimuli from a limited set of interpretable articulatory parameters, a DNN-based internal forward model predicting the sensory consequences of articulatory commands, and an internal inverse model based on a recurrent neural network recovering articulatory commands from the acoustic speech input.
Learning robust speech representation with an articulatory-regularized variational autoencoder
It is increasingly considered that human speech perception and production both rely on articulatory representations.
De b\'e \`a b\'eb\'e : le transfert d'apprentissage auditori-moteur pour interroger l'unit\'e de production de la parole (From sensorimotor experience to speech unit)
Le lien entre ces repr{\'e}sentations se fait-il de mani{\`e}re privil{\'e}gi{\'e}e sur une unit{\'e} sp{\'e}cifique ?
