Abstract
In this paper, we show how adaptive modeling within the statistical parametric speech synthesis framework can be applied to Albanian dialects. We develop speaker dependent voices for the Tosk and Gheg dialect and adapt models for the Gheg dialect from the Tosk models. We show that the adapted Gheg models outperform the speaker dependent Gheg model on an intelligibility and dialect classification task. Furthermore we show that the speaker dependent Tosk model outperforms a formant based synthesizer on an intelligibility, dialect classification and pair-wise comparison task. This formant based synthesizer is the only publicly available synthesizer for Albanian at the moment. We also show that our Gheg and Tosk synthesizers are as intelligible as natural speech. The method where one dialect is modeled through adaptation of a closely related other dialect can be applied to language varieties in general, where the background variety and adapted variety can be chosen based on pragmatic considerations like speaker or data resource availability.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Yamagishi, J., Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T.: A training method of average voice model for HMM-based speech synthesis. IEICE Trans. Fundamentals E86-A(8), 1956–1963 (2003)
Yamagishi, J., Kobayashi, T.: Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training. IEICE Trans. Inf. & Syst. E90-D(2), 533–543 (2007)
Pucher, M., Schabus, D., Yamagishi, Y., Neubarth, F., Strom, V.: Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesis. Speech Communication 52, 164–179 (2010)
eSpeak. eSpeak Text-to-Speech (2007). http://espeak.sourceforge.net/
HTS. HMM-based speech synthesis system (hts) (2014). http://hts.sp.nitech.ac.jp/
Tyshchenko, K.: Metatheory of Linguistics (1999)
Demiraj, S.: Gjuha Shqipe dhe historia e saj. Onufri (2013)
Çabej, E.: Studime gjuh’esore. Rilindja (1976)
Moosmüller, S., Granser, T.: The spread of standard albanian: An illustration based on an analysis of vowels. Language Variation and Change 18, 121–140 (2006)
Papadimitriou, C.: Computational Complexity. Addison Wesley (1994)
Tóth, B., Németh, G.: Improvements of Hungarian Hidden Markov Model-based text-to-speech synthesis. Acta Cybern. 19(4), 715–731 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Pucher, M., Xhafa, V., Dika, A., Toman, M. (2015). Adaptive Speech Synthesis of Albanian Dialects. In: Král, P., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2015. Lecture Notes in Computer Science(), vol 9302. Springer, Cham. https://doi.org/10.1007/978-3-319-24033-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-24033-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24032-9
Online ISBN: 978-3-319-24033-6
eBook Packages: Computer ScienceComputer Science (R0)