Issues of developing software for automating the conduct and verification of dictations
Abstract
Previously, dictations were an integral part of any language learning and learning for better memorization of words and spelling. But at this stage of life, due to various external reasons, education is often forced to be remote. Under these conditions, it became more difficult to carry out this type of work, so writing dictations almost ceased to exist, although this is a very effective form of work. The development of information technology makes it possible to create software for automating the process of conducting dictations. The article presents an analysis of publications in the field of language synthesis methods and the search for similarities between texts. A description of the prototype of the program is presented, which performs the pronunciation of the text and the subsequent verification of the text typed by the user with the original one. The article presents the results of testing the program for different types of errors.
References
2. Brown, P. F., Desouza, P. V., Mercer, R. L., Pietra, V. J. D., and Lai, J. C. Class–based n–gram models of natural language // Computational linguistics. 1992. V. 18. P.467–479.
3. Stratos K. et al. A Spectral Algorithm for Learning Class–Based n–gram Models of Natural Language //UAI. – 2014. – P. 762–771.
4. Kaliyev A., Rybin S.V., Matveev Y. The pausing method based on brown clustering and word embedding // Lecture Notes in Computer Science. 2017. V. 10458. P. 741–747
5. Morise M., Yokomori F., Ozawa K. WORLD: a vocoder–based high–quality speech synthesis system for real–time applications //IEICE TRANSACTIONS on Information and Systems. – 2016. – T. 99. – №. 7. – C. 1877–1884.
