Integration of Neural Network Technologies into Modern Education
Abstract
The article considers an approach to the integration of neural network technologies to eliminate the imbalance between the development of hard (hard skills) and flexible (soft skills) skills in the educational process.The modern labor market requires high communication, creative and logical skills from specialists, but traditional educational programs do not sufficiently focus on soft skills. The authors of the article, based on research by RBC, Google and RSM, emphasize the importance of flexible skills for successful careers and social adaptation, noting that many people have difficulties with communication skills as the fundamental soft skills. To solve this problem, an innovative approach is proposed using neural network technologies to diagnose and develop communication skills. The authors analyze existing deep learning models and propose their own convolutional recurrent neural network (CRNN) structure for diagnosing speech deficiencies in the Russian language. The developed model evaluates pronunciation defects and provides personalized learning materials. The authors propose an interactive educational platform that implements the created model within the framework of hard skills training technology in conjunction with soft skills development programs. The neural network algorithms of the platform optimize the learning process, adapting it to the individual characteristics of the student, and can be used both independently and in addition to classes with a tutor.
References
S. Godin, “Let’s stop calling it soft skills. Talent Management,” in Medium, 2017. [Online]. Available: https://itsyourturnblog.com/lets-stop-calling-them-soft-skills-9cc27ec09ecb
C. R. Mann, A study of engineering education, Joint committee on engineering education of the national engineering societies, New York, USA: New York city, 1918.
K. Nordstrom and J. Ridderstrale, Business in the style of funk. Capital dances to the tune of talent, Moscow: Mann, Ivanov and Ferber, 2013 (in Russian).
T. Yu. Yakuba et al. eds., Soft skills — competencies of the future: a methodological manual / Far Eastern State Scientific Library, department of scientific research and scientific-methodological work, Khabarovsk, Russia: DVGBN, 2023 (in Russian).
A. Nikulina, “7 tips: how to overcome the fear of public speaking,” in ITMO News, 2020. [Online]. Available: https://news.itmo.ru/en/education/trend/news/9396/
M. Alam, M. D. Samad, L. Vidyaratne, A. Glandon, and K. M. Iftekharuddin, “Survey on Deep Neural Networks in Speech and Vision Systems” Neurocomputing, vol. 417, pp. 302–321, 2020; doi: 10.1016/j.neucom.2020.07.053
D. Ribas, M. A. Pastor, A. Miguel, D. Martinez, A. Ortega, and E. Lleida, “Automatic voice disorder detection using self-supervised representations,” IEEE Access, vol. 11, pp. 14915–14927, 2023.
A. A. Joshy and R. Rajan, “Automated dysarthria severity classification: A study on acoustic features and deep learning techniques,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 1147–1157, 2022.
S. Venugopalan et al., “Speech intelligibility classifiers from 550 disordered speech samples,” 2023, arXiv:2303.07533v2 [eess.AS].
A. A. Khomenko, I. V. Zinchenko, and Yu. V. Bryzgalova, “Diagnostika rechevyh narusheniya u doshkolnikov s pomoshchyu iskusstvennogo intellekta” [Artificial intelligence as a diagnostic technology for detecting speech disorders], Pedagogical Perspective, vol. 13, no. 1, pp. 58–65, 2024 (in Russian); doi:10.55523/27822559_2024_1(13)_58
L. V. Savchenko, “Computer-Assisted Language Learning Based on Convolutional Neural Networks and Information Theory of Speech Perceptio,” Information Technologies, vol. 25, no. 5, pp. 313–319, 2019 (in Russian); doi:10.17587/it.25.313-318
A. Graves, A. Mohamed, and G. Hinton, “Speech recognition with deep recurrent neural networks,” in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 2013, pp. 6645–6649, 2013; doi:10.1109/ICASSP.2013.6638947
T. N. Sainath, A. Mohamed, B. Kingsbury, and B. Ramabhadran, “Deep Convolutional Neural Networks for LVCSR,”in Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, Canada, 2013, pp. 8614–8618, 2003; doi:10.1109/ICASSP.2013.6639347
G. Surbhi, K. Sham, A. T. Kalai and Z. Cyril, “Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms,” 2022, arXiv:2209.00735v2 [cs.LG].
O. Pronina and O. Piatykop, “The recognition of speech defects using convolutional neural network,” CTEWorkshop Proceedings, vol. 10, pp. 153–166, 2023; doi:10.55056/cte.554
L. D. Alferova, Rechevoj trening: dikcija i proiznoshenie. Posobie [Diction and pronunciation. Manual], St. Petersburg, Russia: RGISI, 2003 (in Russian).
L. V. Lopatina, “Proyavleniya i diagnostika foneticheskih narusheniya pri stertoj dizartrija” [Manifestations diagnosis of phonetic disorders in erased dysarthria], Izvestiya RGPU im. A. I. Gertsena, vol. 6, no. 14, pp. 219–230, 2006 (in Russian).
This work is licensed under a Creative Commons Attribution 4.0 International License.
