Search Results for author:
Found 4 papers, 1 papers with code
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.
Dynamical Variational Autoencoders: A Comprehensive Review
Recently, a series of papers have presented different extensions of the VAE to process sequential data, which model not only the latent space but also the temporal dependencies within a sequence of data vectors and corresponding latent vectors, relying on recurrent neural networks or state-space models.
Mod\'elisation bay\'esienne de la planification motrice des gestes de parole: \'Evaluation du r\^ole des diff\'erentes modalit\'es sensorielles (Bayesian modeling of speech gesture motor planning: Evaluating the role of different sensory modalities )
Nous proposons d{'}explorer le r{\^o}le de ces modalit{\'e}s sensorielles dans la planification des gestes de parole {\`a} partir d{'}un mod{\`e}le bay{\'e}sien repr{\'e}sentant la structure des connaissances mises en jeu dans cette t{\^a}che.
