Forward Dynamics Modeling of Speech Motor Control Using Physiological Data
Abstract
We propose a paradigm for modeling speech production based on neural networks. We focus on characteristics of the musculoskeletal system. Using real physiological data - articulator movements and EMG from muscle activity(cid:173) a neural network learns the forward dynamics relating motor commands to muscles and the ensuing articulator behavior. After learning, simulated perturbations, were used to asses properties of the acquired model, such as natural frequency, damping, and interarticulator couplings. Finally, a cascade neural network is used to generate continuous motor commands from a sequence of discrete articulatory targets.
Cite
Text
Hirayama et al. "Forward Dynamics Modeling of Speech Motor Control Using Physiological Data." Neural Information Processing Systems, 1991.Markdown
[Hirayama et al. "Forward Dynamics Modeling of Speech Motor Control Using Physiological Data." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/hirayama1991neurips-forward/)BibTeX
@inproceedings{hirayama1991neurips-forward,
title = {{Forward Dynamics Modeling of Speech Motor Control Using Physiological Data}},
author = {Hirayama, Makoto and Vatikiotis-Bateson, Eric and Kawato, Mitsuo and Jordan, Michael I.},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {191-198},
url = {https://mlanthology.org/neurips/1991/hirayama1991neurips-forward/}
}