ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Articulatory trajectories generated by the control of the vocal tract by a neural network

Martine George, Paul Jospa, Alain Soquet

In this paper, we present a method of generating articulatory trajectories from formant transitions. A multilayer feedforward neural network controls a vocal tract model on the basis of its first three resonances (the formants) in order to compute 8 articulatory parameters (the cross sectional areas of 7 regions of the Distinctive Regions Model and the vocal tract length). 4 learning modes have been studied and compared: autonomous, supervised, hybrid and supervised-hybrid. After training in one of the 4 modes, the neural network is able to generate articulatory configurations. Each formant triplet time sample is successively introduced into the network. For each triplet, a local optimisation is performed by the neural network in an autonomous learning mode. Several articulatory trajectories are presented.


Cite as: George, M., Jospa, P., Soquet, A. (1994) Articulatory trajectories generated by the control of the vocal tract by a neural network. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 583-586

@inproceedings{george94_icslp,
  author={Martine George and Paul Jospa and Alain Soquet},
  title={{Articulatory trajectories generated by the control of the vocal tract by a neural network}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={583--586}
}