Recent Results in Speech Recognition for the Tatar Language

  • Aidar KhusainovEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10415)


This paper presents a comparative study of several different systems for speech recognition for the Tatar language, including systems for very large and unlimited vocabularies. All the compared systems use a corpus based approach, so recent results in speech and text corpora creation are also shown. The recognition systems differ in acoustic modelling algorithms, basic acoustic units, and language modelling techniques. The DNN based system with the sub-word based language model shows the best recognition result obtained on the test part of speech corpus.


Speech recognition Acoustic modelling Language modelling Tatar language 


  1. 1.
    Yandex translate (2017).
  2. 2.
    Khusainov, A.: Design and creation of speech corpora for the Tatar speech recognition and synthesis tasks. In: Proceedings of Third International Conference on Turkic Languages Processing TurkLang-2015, Kazan, Russia, pp. 475–484 (2015)Google Scholar
  3. 3.
    Khusainov, A.: Speech human-machine interface for the Tatar language, FRUCT Oy, Helsinki, pp. 60–65 (2016)Google Scholar
  4. 4.
    Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., et al.: The Kaldi speech recognition toolkit. In: Proceedings of ASRU, pp. 1–4 (2011)Google Scholar
  5. 5.
    Suleymanov, D., Nevzorova, O.A., Khakimov, B.: National corpus of the Tatar language Tugan tel: structure and features of grammatical annotation. In: Proceedings International Conference Georgian Language and Modern Technology, Tbilisi, pp. 107–108 (2013)Google Scholar
  6. 6.
    Khusainov, A.: Tekhnologiya avtomatizatsii sozdaniya I otsenki kachestva programmnikh sredstv analiza rechi c uchetom osobennostey maloresursnykh yazikov. Ph.D. thesis, Kazan (2014)Google Scholar
  7. 7.
    Krauwer, S.: The basic language resource kit (BLARK) as the first milestone for the language resources roadmap. In: Proceedings of International Workshop Speech and Computer SPEECOM, Moscow, Russia, pp. 8–15 (2003)Google Scholar
  8. 8.
    Lewis, M., Paul Simons, G.F., Fennig, C.D. (eds.): Ethnologue: Languages of the World, 9th edn. (2016). Accessed 15 Jan 2017
  9. 9.
    Kneser, R., Ney, H.: Improved backing off for m-gram language modeling. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 1 (1995)Google Scholar
  10. 10.
    Rath, S.P., Povey, D., Vesely, K., Cernocky, J.H.: Improved feature processing for deep neural networks. In. Proceedings of InterSpeech (2013)Google Scholar
  11. 11.
    Stolcke, A.: Entropy-based pruning of backoff language models. In: Proceedings DARPA Broadcast News Transcription and Understanding Workshop, Lansdowne, pp. 270–274 (1998)Google Scholar
  12. 12.
    Stolcke, A.: SRILM an extensible language modeling toolkit. In: Proceedings of International Conference on Spoken Language Processing, Denver, vol. 2, pp. 901–904 (2002)Google Scholar
  13. 13.
    Robeiko, V., Sazhok, M.: Bidirectional text-to-pronunciation conversion with word stress prediction for Ukranian. In: Proceedings UkrObraz 2012, Kyiv, pp. 43–46 (2025)Google Scholar
  14. 14.
    Zhang, X., Trmal, J., Povey, D., Khudanpur, S.: Improving deep neural network acoustic models using generalized maxout networks. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 215–219 (2014)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Institute of Applied Semiotics of the Tatarstan Academy of SciencesKazan Federal UniversityKazanRussia

Personalised recommendations