Finding Intelligible Consonant-Vowel Sounds Using High-Quality Articulatory Synthesis

Daniel R. van Niekerk, Anqi Xu, Branislav Gerazov, Paul K. Krug, Peter Birkholz, Yi Xu


In this study, a state-of-the-art articulatory speech synthesiser was used as the basis for simulating the exploration of CV sounds imitating speech stimuli. By adopting a relevant kinematic model and systematically reducing the search space of consonant articulatory targets, intelligible CV sounds can be found. Derivative-free optimisation strategies were evaluated to speed up the process of exploring articulatory space and the possibility of using automatic speech recognition as a means of evaluating intelligibility was explored.


 DOI: 10.21437/Interspeech.2020-2545

Cite as: Niekerk, D.R.V., Xu, A., Gerazov, B., Krug, P.K., Birkholz, P., Xu, Y. (2020) Finding Intelligible Consonant-Vowel Sounds Using High-Quality Articulatory Synthesis. Proc. Interspeech 2020, 4457-4461, DOI: 10.21437/Interspeech.2020-2545.


@inproceedings{Niekerk2020,
  author={Daniel R. van Niekerk and Anqi Xu and Branislav Gerazov and Paul K. Krug and Peter Birkholz and Yi Xu},
  title={{Finding Intelligible Consonant-Vowel Sounds Using High-Quality Articulatory Synthesis}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={4457--4461},
  doi={10.21437/Interspeech.2020-2545},
  url={http://dx.doi.org/10.21437/Interspeech.2020-2545}
}