An Interactive Oral Training Platform Based on Kinect for EFL Learning

Abstract:

Nowadays, the emphasis of domestic oral English teaching is on grammar and pronunciation. Although many achievements have been made and theories have been established in this field, there are still some deficiencies in such traditional methodologies. Because of the lack of corresponding technologies and practices, few explorations have been made in how to make communication more effective and accurate by both verbal and nonverbal means such as facial expressions and gestures. It is not difficult to understand why the Chinese learners give native speakers the expression that they are dull and uninterested. For the aforementioned problems, in this paper, characterizing a combination of the latest biometric technology (recognition of voices, facial expressions and body movements) and Kinect, an interactive oral English training platform is designed. This platform targets training students' not only verbal but also nonverbal language abilities including pronunciation, intonation, especially facial expressions, body languages. With the evaluation of the practical application of the platform, it proves to be an effective way of improving their overall oral English abilities.

• Periodical: Applied Mechanics and Materials (Volume 704)
• Pages: 419-423
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.704.419
• Online since: December 2014
• Authors: Yang Rui Zhang*, Guang Huo, Jian Feng Wu, Jun Bo Yang, Chen Pang
• Keywords: Facial Expression Recognition, KINECT, Motion Recognition, Oral English Learning

References

[1] Mehrabian A, Russell J A. An approach to environmental psychology [M]. the MIT Press, (1974).

[2] Hong Aozhou. The Exploration and Analysis of the Strategy on Learning Context of Spoken Foreign Languages [J]. Journal of Sichuan Engineering Technical College, 2012, 26(2): 65-66.

[3] Leyvand T, Meekhof C, Wei Y C, et al. Kinect identity: Technology and experience [J]. Computer, 2011, 44(4): 94-96.

DOI: 10.1109/mc.2011.114

[4] Hsu H J. The potential of Kinect in education [J]. International Journal of Information and Education Technology, 2011, 1(5): 365-370.

[5] Ma L, Khorasani K. Facial expression recognition using constructive feedforward neural networks[J]. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 2004, 34(3): 1588-1595.

DOI: 10.1109/tsmcb.2004.825930

[6] Long F, Wu T, Movellan J R, et al. Learning spatiotemporal features by using independent component analysis with application to facial expression recognition[J]. Neurocomputing, 2012, 93: 126-132.

DOI: 10.1016/j.neucom.2012.04.017