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
Konferenzbeitrag | Veröffentlicht | Englisch
Abstract / Bemerkung
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.
Erscheinungsjahr
Konferenz
Forth Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob)
Konferenzort
Genoa, Italy
Konferenzdatum
2014-10-13 – 2014-10-16
PUB-ID

Zitieren

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. doi:10.1109/DEVLRN.2014.6982981
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.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2018-01-12T13:51:59Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar