Total views : 142

Language Models Creation for the Tatar Speech Recognition System


  • Kazan Federal University, Kazan, Kremlevskaya st., 18, Institute of Applied Semiotics of the Tatarstan Academy of Sciences, Kazan, Levo-Bulachnaya st., 36a, Russian Federation


Objectives: The article presents the experiments on the creation of different language models for the Tatar language. N-gram statistical models are used with five different smoothing techniques. Methods: These models can be used in various applications: machine translation systems, spell checking, etc. The study intended to use the patterns in the system of Tatar speech automatic recognition. Taking into account the specifics of the Tatar language, consisting in a rich morphology, speech recognition systems may use not only words but also the building blocks of words as basic modeling units: syllables, morphemes, etc Finding: The following essential elements were chosen for a complete analysis of Tatar language models development: word, morpheme, morph (statistically selected component of a nutshell), the stem and affix chain, syllable and letter. Thus, some models constructed for all combinations of 2-, 3-, 4-grams, smoothing techniques and essential elements of the language. Besides, an experiment showing the possibility of a language model development based on word classes conducted. Conclusion: According to performed experiment results the conclusions are made about the quality of the Tatar language grammar description, the degree of coverage lexicon, and required vocabulary volume for each type of constructed models.


Automatic Speech Recognition, Class-Based Models, Language Model, N-Grams, Tatar Language

Full Text:

 |  (PDF views: 152)


  • Speech recognition grammar specification version 1.0 [Internet]. 2014 [cited 2014 Mar 16]. Available from:
  • Manning CD, Schutze H. Foundations of statistical natural language processing. MIT – Press: Cambridge, Massachusetts; 1999. p. 704.
  • Shamna TC, Baiju KC. The emerging issues of immigrant labourers in the construction sector of Kerala. Indian Journal of Economics and Development. 2016; 4(2):1–12.
  • Srinivasan S. an exclusive cache architecture with power saving. Indian Journal of Science and Technology. 2015 Dec; 8(33):1–5.
  • Kipyatkova IS, Karpov AA. The development and research of Russian language statistical model. Trudy SPIIRAN proceedings.2010; 12:35–49.
  • Bayestehtashk A, Shafran I, Babaeian A. Robust speech recognition using multivariate copula models. In Institute of Electrical and Electronics Engineers (IEEE) International Conference on Acoustics, Speech and Signal Processing; 2016 Mar. p. 5890–4.
  • Khusainov A, Suleymanov D. Language identification system for the Tatar language. Speech and Computer, Lecture Notes in Computer Science, Springer. 2013; 8113:203–10.
  • Mathias C, Lagus K. Unsupervised discovery of morphemes.In the Proceedings of the Workshop on Morphological and Phonological Learning of Association for Computational Linguistics; 2002. p. 21–30.
  • Suleymanov D, Nevzorova OA, Khakimov B. National corpus of the Tatar language Tugan Tel: structure and features of grammatical annotation. Procedia - Social and Behavioral Sciences. 2013 Oct; 95:68–74.
  • Brown PF, Pietra VJD, Souza PVD. Class-based N-gram models of natural language. Computational Linguistics.1992 Dec; 18(4):467–79.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.