Physiologically Based Speech Synthesis

Makoto Hirayama, Eric Vatikiotis-Bateson, Kiyoshi Honda, Yasuharu Koike, Mitsuo Kawato

NeurIPS 1992 pp. 658-665

/neurips/1992/hirayama1992neurips-physiologically/

Abstract

This study demonstrates a paradigm for modeling speech produc(cid:173) tion based on neural networks. Using physiological data from speech utterances, a neural network learns the forward dynamics relating motor commands to muscles and the ensuing articulator behavior that allows articulator trajectories to be generated from motor commands constrained by phoneme input strings and global performance parameters. From these movement trajectories, a sec(cid:173) ond neural network generates PARCOR parameters that are then used to synthesize the speech acoustics.

PDF NeurIPS Semantic Scholar

Cite

Text

Hirayama et al. "Physiologically Based Speech Synthesis." Neural Information Processing Systems, 1992.

Markdown

[Hirayama et al. "Physiologically Based Speech Synthesis." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/hirayama1992neurips-physiologically/)

BibTeX

@inproceedings{hirayama1992neurips-physiologically,
  title     = {{Physiologically Based Speech Synthesis}},
  author    = {Hirayama, Makoto and Vatikiotis-Bateson, Eric and Honda, Kiyoshi and Koike, Yasuharu and Kawato, Mitsuo},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {658-665},
  url       = {https://mlanthology.org/neurips/1992/hirayama1992neurips-physiologically/}
}