Abstract
This paper presents the methods used and results obtained for the creation of a Festival-compatible pronunciation dictionary of above 10k words for the kabyle language. Kabyle is a berber dialect spoken in Northern Algeria. This dictionary will be useful in the design of text-to-speech and automatic speech recognition systems for the kabyle language. It was built using a bootstrapping method in which we incrementally build rules to predict word pronunciations while correcting wrong predictions. We thus obtain a large pronunciation dictionary as well as a set of rules to predict pronunciations for unknown words. The rules are embedded in Classification and Regression Trees and achieve 91,62% of correct prediction rate for entire words and 97,85% for phonemes.
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
Kossmann, M.G., Stroomer, H.J.: Phonologies of Asia and Africa, 1st edn. Eisenbrauns, Winona Lake (1997)
The Unicode Consortium: The Unicode Standard, Version 4.1.0, defined by: The Unicode Standard, Version 4.0, as amended by Unicode 4.0.1 and by Unicode 4.1.0. Addison-Wesley, Boston (2003)
Maskey, S.R., Black, A.W., Tomokiyo, L.M.: Bootstrapping phonetic lexicons for new languages. In: International Conference on Speech and Language Processing 2004, pp. 69–72. ISCA, Jeju Island (2004)
Black, A., Lenzi, K., Pagel, V.: Issues in building general letter to sound rules. In: 3rd ESCA Workshop on Speech Synthesis, pp. 77–80. Jenolan Caves, Australia (2004)
Davel, M., Barnard, E.: Pronunciation prediction with default&refine. Comput. Speech Lang. 22(4), 374–393 (2008)
Bisani, M., Hermann, N.: Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun. 50(5), 434–451 (2008)
Jyothi, P., Hasegawa-Johnson, M.: Low-resource grapheme-to-phoneme conversion using recurrent neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, New Orleans (2017)
Razavi, M., Rasipuram, R., Doss, M.M.: Pronunciation lexicon development for under-resourced languages using automatically derived subword units: a case study on Scottish Gaelic. In: Proceedings of 4th Biennial Workshop on Less-Resourced Languages, pp. 1–2. Society for Language Resources and Technology, Poznan (2015)
Razavi, M., Rasipuram, R., Doss, M.M.: Towards weakly supervised acoustic subword unit discovery and lexicon development using hidden Markov models. Speech Commun. 96, 168–183 (2018)
The Festival Speech Synthesis System System Documentation. http://www.festvox.org/docs/manual-2.4.0/festival_toc.html. Accessed 31 Mar 2019
Inkpen, D., Frunza, O., Kondrak, G: Automatic identification of cognates and false friends in French and English. In: Proceedings of the International Conference Recent Advances in Natural Language Processing, pp. 251–257. Bulgarian Academy of Sciences, Borovets (2005)
Montalvo, S., Pardo, E.G., Martinez, R., Fresno, V..: Automatic cognate identification based on a fuzzy combination of string similarity measures. In: 2012 IEEE International Conference on Fuzzy Systems. IEEE, Brisbane (2012)
Brew, C., McKelvie, D.: Word-pair extraction for lexicography. In: Oflazer, K., Somers, H. (eds.) Proceedings of the 2nd International Conference on New Methods in Language Processing, Ankara, Bilkent University, pp. 45–55 (1996)
Davel Marelie, H.: Pronunciation Modelling and Bootstrapping. (Thesis), University of Pretoria, p. 99 (2005)
Faizi, R.: Stress systems in Amazigh: a comparative study. Revue Asinag 6, 115–127 (2011)
Roettger, T.B., Bruggeman, A., Grice, M.: Word stress in Tashlhiyt-Post lexical prominence in disguise? In: Proceedings of 18th International Congress on Phonetic Sciences. International Phonetic Association, London/Glasgow (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Lyes, D., Leila, F., Hocine, T. (2019). Building a Pronunciation Dictionary for the Kabyle Language. In: Salah, A., Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2019. Lecture Notes in Computer Science(), vol 11658. Springer, Cham. https://doi.org/10.1007/978-3-030-26061-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-26061-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26060-6
Online ISBN: 978-3-030-26061-3
eBook Packages: Computer ScienceComputer Science (R0)