Abstract
In this study, an experiment is conducted to explore and exploit shared Amharic and Tigrigna syllables in the development of Amharic Tigrigna bilingual text to speech synthesizer. Both Amharic and Tigrigna are under resourced languages, yet these two languages share the Geez writing system with large portion of phone sets and syllables. This study therefore shows the possibility of constructing Amharic-Tigrigna bilingual text to speech synthesizer based on the shared syllables to optimize linguistic resources. The dataset for training and testing is composed of consonant-vowel syllables in both languages. Festival speech synthesis framework is used for the experiment. The result shows mean opinion score of 3.09 and 2.08 for intelligibility and naturalness, respectively. Epenthesis vowel insertion and possibility geminates which are not predictable from the text at surface level in both languages greatly affect naturalness of the synthetic speech. Another factor that affects the naturalness is the fact that we used an already existing multilingual speech synthesis framework that has foreign accent. Even though the naturalness is below average because of the aforementioned reasons, the possibility of exploiting shared features to develop multilingual speech synthesis for under resourced languages is encouraging. We have learned that to enhance the performance of the bilingual synthesizer, there is a need to integrate language specific features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Taylor, P.: Text to Speech Synthesis. Cambridge University Press, New York (2009)
Strout, R., Olive, J.: Text to speech synthesis. In: Vijay, D.B.W., Madisetti, K. (ed.) Digital Signal Processing Handbook, pp. 976–986. CRC Press, Lonndon (1999)
Lemmetty, S.: Review of Speech Synthesis Technologies. Helsinki University of Technology, Helsinki (1999)
Sagisak, Y.: Spoken output technologies. In: Survey of the State of the Art in Human Language Technology, pp. 165–197. Cambidge University Press, Cambidge (1997)
Laine, B.: Text to Speech Synthesis for Amharic Language. Addis Ababa University, Addis Ababa (1999)
Henock, L.: Concatenative Text to Speech Synthesis for Amharic language. Addis Ababa Univerity, Addis Ababa (2003)
Tesfay, Y.: Diphone Based Text to Speech Synthesis for Tigrigna language. Addis Ababa University, Addis Ababa (2004)
Nadew, T.: Formant Based Synthesis for Amharic Vowels. Addis Ababa University, Addis Ababa (2008)
Bereket, K.: Developing a Speech Synthesizer for Amharic using Hidden Markov Model. Addis Ababa University, Addis Ababa (2008)
Alula, T.: A Generalized Approach to Amharic Text to Speech (TTS) Synthesis System. Addis Ababa University, Addis Ababa (2010)
Lemlem, H., Million, M.: Text to speech synthesis for ethiopian semitic languages: issues and the way forward. In: 12th IEEE Africon International Conference, Addis Ababa (2015)
Chen, Y.-J., Tu, T., Yeh, C.-C., Lee, H.-Y.: End-to-end text-to-speech for low-resource languages by cross-lingual transfer learning. arXiv e-print arXiv:1904.06508v2 (2019)
Lee, Y., Shon, S., Kim, T.: Learning pronunciation from a foreign language in speech synthesis networks. arXiv e-prints: arXiv.1811.09364v4 (2020)
Bender, L., Hailu, F.: Amharic Verb Morphology: A Generative Approach, Michiga Michiga State University (1978)
Ethnologue Homepage. https://www.ethnologue.com. Accessed 15 June 2017
Girmay, B.: The Phonology of Tigrigna: Generative Approach. Addis Ababa University, Addis Ababa (1983)
Tsehaye, T.: Reference Grammar of Tigrigna. Georgetown University, Washignton DC (1979)
Daniel, T.: Modern Tigrigna Grammar. Biranna Press, Addis Ababa (2008)
Baye, Y.: Amharic Grammar. Elleni Press, Addis Ababa (2007)
Mulugeta, S.: The Syllable Structure and Syllabification in Amharic. Norwegian University of Science and Technology, Oslo (2001)
Tesfay, T.: A Modern Grammar of Tigrigna, Tipografia U. Detti, Rom (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Hagos, L., Meshesha, M., Atnafu, S., Teferra, S. (2022). Shared Syllables for Amharic Tigrigna Text to Speech Synthesis. In: Berihun, M.L. (eds) Advances of Science and Technology. ICAST 2021. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 411. Springer, Cham. https://doi.org/10.1007/978-3-030-93709-6_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-93709-6_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-93708-9
Online ISBN: 978-3-030-93709-6
eBook Packages: Computer ScienceComputer Science (R0)