Abstract
This research project proposes a prototype design for a refreshable braille display to convert Bangla Speech to Braille output. It aims to be a communication and learning module for deaf-blind or blind people to pursue inclusive education. First, we took speech input from a transducer, and speech recognition was done by DeepSpeech, a Natural Language Processing framework developed by Mozilla. Then, the converted text output was linked with its corresponding braille pins and was shown in a refreshable braille display. Finally, the entire computation was carried away by a Raspberry Pi. We have proposed the usage of our prototype as a special ICT device in the journey towards inclusive education in Bangladesh. In addition, future development has been suggested to broaden the periphery of the project.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
WHO Media Centre. Visual impairment and blindness. http://www.who.int/mediacentre/factsheets/fs282/en/ (2013). Accessed 15 March 2014
United Nations. Factsheet on Persons with Disabilities. http://www.un.org/disabilities/default.asp?id=18 (2013). Accessed 25 May 2013
Mitra, S., Posarac, A., Vick, B.: Disability and poverty in developing countries: a snapshsot from the World Health Survey. (World Bank Sp discussion paper (1109)), The World Bank, Washington, DC, USA (2011)
Rahman, K.F.: Blindness, ‘Vision 2020 and Bangladesh. Finan. Express 20(436), 10 (2012)
Das, A.: Inclusion of student with disabilities in mainstream primary education of Bangladesh. J. Int. Dev. Cooper. 17(2), 1–10 (2011)
EFA Global Monitoring Report 2010. Reaching the Marginalized. United Nations Educational, Scientific and Cultural Organization. Oxford University Press, Oxford, UK
Hirayama, M.J.: Digital talking book contents of beading handicraft design diagram for visually impaired persons. In: 4th International Conference on Interaction Sciences (ICIS), pp. 96–101, Busan, South Korea (2011)
Paul, A.K., Das, D., Kamal, M.M.: Bangla speech recognition system using lpc and ann. In: 2009 Seventh International Conference on Advances in Pattern Recognition, pp. 171–174, February 2009.
Ahammad, K., Rahman, M.M.: Connected Bangla speech recognition using artificial neural network. Int. J. Comput. Appl. 149(9), 38–41 (2016)
Park, A.S., Glass, J.R.: Unsupervised pattern discovery in speech. IEEE Trans. Audio Speech Language Process. 16(1), 186–197 (2008)
Kamper, H., Jansen, A., Goldwater, S.: Unsupervised word segmentation and lexicon discovery using acoustic word embeddings. IEEE/ACM Trans. Audio Speech Language Process. (TASLP), 24(4), 669–679 (2016)
Bansal, S., Kamper, H., Lopez, A., Goldwater, S.: Towards speech-to-text translation without speech recognition. arXiv preprint arXiv:1702.03856 (2017)
Honglak Lee, Peter Pham, Yan Largman, and Andrew Y. Ng. Unsupervised fea- ture learning for audio classification using convolutional deep belief networks. In Y. Bengio, D. Schuurmans, J. D. Lafferty, C. K. I. Williams, and A. Culotta, editors, Advances in Neural Information Processing Systems 22, pages 1096–1104. Curran Associates, Inc., 2009.
Hannun, A. et al.: Deep speech: scaling up end-to-end speech recognition. Baidu Research – Silicon Valley AI. arXiv:1412.5567v2. [cs.CL], 19 December 2014
Sultana, S., Akhand, M.A.H., Das, P.K., Rahman, M.H.: Bangla speech-to-text conversion using SAPI. In: 2012 International Conference on Computer and Communication Engineering (ICCCE), pp. 385–390 (2012)
Sabab, M., Chowdhury, M.A.R., Nirjhor, S.M., Uddin, J.: Bangla speech recognition using 1D-CNN and LSTM with different dimension reduction techniques. In: International Conference for Emerging Technologies in Computing, pp. 158–169. Springer, Cham (2020).
Maruf, M., Faruque, M., Muhtasim, M., Nelima, N.N., Mahmood, S., Riad, M., Uddin, M.: Comparative study of effective augmentation method for Bangla ASR using convolutional neural network.” In: Emerging Technologies in Data Mining and Information Security, pp. 203–213. Springer, Singapore (2021)
Large Bengali ASR training data set. https://tinyurl.com/Open-SLR
Bangla Text to Braille code (2021). https://tinyurl.com/Bangla-Text2Brail
Shobdo-Kolpo-Drum/Project-codes (2021). https://github.com/Shobdo-Kolpo- Drum/Project-codes
AudioConverter 0.3.0. https://pypi.org/project/AudioConverter/
Mozilla/DeepSpeech. https://github.com/mozilla/DeepSpeech
Simulated circuit design.fzz (2021). https://tinyurl.com/Circuit-Design-A25
Shobdo Koplo Drum (2021). https://tinyurl.com/Shobdo-kolpo-drum
Group A25 Demo (2021). https://tinyurl.com/Group-A25
Hossain, S.A. et al.: Bangla braille adaptation. In: Technical Challenges and Design Issues in Bangla Language Processing, Chapter 2 (2013)
Acknowledgements
At first, we would like to thank our family members, especially our parents. Without their hospitality, the project would not be possible in the lockdown due to the Covid-19 situation. Next, we are ever grateful to Satyaki Banik and Nusrat Binte Nizam, who greatly encouraged us to take up a project to bridge the gap between Bangla Natural Language Processing (NLP) and Mechanical Engineering. We want to thank Apurba Sarker for his initial involvement in preparing DeepSpeech Framework, Rasman Mubtasim Swargo, and Aniruddha Ganguli for their knowledgeable suggestions regarding NLP. Finally, we are grateful to Partha Pratim Das for the Google Colab Pro Support and Shakti Banik for his contribution in conceptualizing the design.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rahim, R.R., Al Nahian, A.I., Kalam, R.B., Gupta, A.S., Nizam, N.B. (2022). Bangla Speech-To-Braille Interaction Device for Visual and Hearing Impaired. In: Hossain, S., Hossain, M.S., Kaiser, M.S., Majumder, S.P., Ray, K. (eds) Proceedings of International Conference on Fourth Industrial Revolution and Beyond 2021 . Lecture Notes in Networks and Systems, vol 437. Springer, Singapore. https://doi.org/10.1007/978-981-19-2445-3_47
Download citation
DOI: https://doi.org/10.1007/978-981-19-2445-3_47
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2444-6
Online ISBN: 978-981-19-2445-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)