Konferenzpaper | 2014 | Peer reviewed

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

Autor(en)

Philippsen, Anja ; Reinhart, Felix ; Wrede, Britta

Name der Konferenz

Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob)

DOI

10.1109/DEVLRN.2014.6982981

URN

urn:nbn:de:0070-pub-27002644

URL

https://pub.uni-bielefeld.de/record/2700264

Weitere Details

Sprache

englisch

Darstellungsform

Text

Link zum Volltext (intern)

https://pub.uni-bielefeld.de/record/2700264

DDC

006

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.

Zitierstile

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.

In die Zwischenablage einfügen

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. doi:10.1109/DEVLRN.2014.6982981

In die Zwischenablage einfügen

Philippsen, Anja, Reinhart, Felix, and Wrede, Britta. 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 .

In die Zwischenablage einfügen

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.

In die Zwischenablage einfügen

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.

In die Zwischenablage einfügen

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.

In die Zwischenablage einfügen

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).

In die Zwischenablage einfügen

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.

AMA

APA (6th ed.)

Chicago

Frontiers

Harvard

IEEE

LNCS

MLA