Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model

Philippsen A, Reinhart F, Wrede B (2014)
Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy.

Download
OA
Conference Paper | Published | English
Abstract
This paper proposes an efficient neural network model for learning the articulatory-acoustic forward and inverse mapping of consonant-vowel sequences including coarticulation effects. It is shown that the learned models can generalize vowels as well as consonants to other contexts and that the need for supervised training examples can be reduced by refining initial forward and inverse models using acoustic examples only. The models are initially trained on smaller sets of examples and then improved by presenting auditory goals that are imitated. The acoustic outcomes of the imitations together with the executed actions provide new training pairs. It is shown that this unsupervised and imitation-based refinement significantly decreases the error of the forward as well as the inverse model. Using a state-of-the-art articulatory speech synthesizer, our approach allows to reproduce the acoustics from learned articulatory trajectories, i.e. we can listen to the results and rate their quality by error measures and perception.
Publishing Year
Conference
Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob)
Location
Genoa, Italy
Conference Date
2014-10-13 – 2014-10-16
PUB-ID

Cite this

Philippsen A, Reinhart F, Wrede B. Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy.
Philippsen, A., Reinhart, F., & Wrede, B. (2014). Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy.
Philippsen, A., Reinhart, F., and Wrede, B. (2014).“Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model”. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy.
Philippsen, A., Reinhart, F., & Wrede, B., 2014. Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy.
A. Philippsen, F. Reinhart, and B. Wrede, “Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model”, Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy, 2014.
Philippsen, A., Reinhart, F., Wrede, B.: Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy (2014).
Philippsen, Anja, Reinhart, Felix, and Wrede, Britta. “Learning How to Speak: Imitation-Based Refinement of Syllable Production in an Articulatory-Acoustic Model”. Presented at the Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), Genoa, Italy, 2014.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2015-01-27 15:54:12

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar