Simulation of vocalic gestures using an articulatory model driven by a sequential neural network

The “sequential neural network” proposed by Jordan (MIT COINS Technical Report 88‐27, 1988) enables learning of motor skill problems involving excess degrees of freedom. This structure was used with (i) the articulatory model developed by Meada [J. Acoust. Soc. Am. Suppl. 1 65, S22 (1979)] as an internal “forward” model relating a given set of articulatory commands (five articulators, e.g., lips, jaws, tongue body, tongue dorsum, and tongue tip) to their acoustic consequences, (ii) vocalic targets specified in the formant (F1, F2, F3) space, and (iii) smoothness constraints leading to coarticulation phenomena. A first set of results about learning of such vocalic gestures will be presented and the following will be discussed: (i) the pattern of coarticulation phenomena observed in this structure, such as between‐articulator relationships for achieving a given formant target and temporal organization of the trajectories in the articulatory space, (ii) the role of gesture duration, and (iii) the compensatio...