Mobile Base Sinhala Book Reader for Visually Impaired Students
Abstract
The project aims to improve the reading
experience and skills of visually impaired students in Sri Lanka by creating a
mobile application that allows them to easily read printed books and stationery
in Sinhala. The mobile application uses optical character recognition (OCR)
technology and voice navigation, incorporating text-to-speech features of the
event synthesis framework. The application accurately captures characters on a
page of a Sinhala book and distinguishes them using OCR technology, enabling visually
impaired people to convert text into accessible digital formats. The extracted
text is then made audible via text-to-speech. Sinhala Voice Navigation support
is provided for users to navigate the app, get feedback from the user, and
identify objects in the surrounding room. The application uses image
recognition and description algorithms to describe pictures in Sinhala, helping
visually impaired children understand the visual content and improve their
reading skills. The platform also offers features to adjust reading speed and
choose between male or female voices.
WHO, World report on vision,
vol. 214, no. 14. 2019. [Online]. Available:
https://www.who.int/publications-detail/world-report-on-vision.
D. S. S. De Zoysa, J. M.
Sampath, E. M. P. De Seram, D. M. I. D. Dissanayake, L. Wijerathna, and S.
Thelijjagoda, “Project Bhashitha - Mobile based optical character recognition
and text-to-speech system,” 13th Int. Conf. Comput. Sci. Educ. ICCSE 2018, no.
Iccse, pp. 623–628, 2018, doi: 10.1109/ICCSE.2018.8468858.
A.Joy* and D. R. Saranya, “A
Pilot Research on Android Based Voice Recognition Application,” Int. J. Recent
Technol. Eng., vol. 8, no. 4, pp. 7272–7277, 2019, doi:
10.35940/ijrte.d5284.118419.
S. Chanda, S. Pal, and U.
Pal, “Word-wise Sinhala Tamil and English script identification using Gaussian
kernel SVM,” Proc. - Int. Conf. Pattern Recognit., no. February 2015, 2008,
doi: 10.1109/icpr.2008.4761823.
S. Gallege, “Analysis of
Sinhala Using Natural Language Processing Techniques,” 2010, [Online].
Available: www.defence.lk/
M. Rimas, R. P. Thilakumara,
and P. Koswatta, “Optical character recognition for Sinhala language,” c2013
IEEE Glob. Humanit. Technol. Conf. South Asia Satell. GHTC-SAS 2013, no.
August, pp. 149–153, 2013, doi: 10.1109/GHTC-SAS.2013.6629906.
D. L. Pennell and Y. Liu,
“NORMALIZATION OF TEXT MESSAGES FOR TEXT-TO-SPEECH The University of Texas at
Dallas Computer Science Department 800 West Campbell Road,” 2010 IEEE Int.
Conf. Acoust. Speech Signal Process., pp. 4842–4845, 2010.
S. Ueno, M. Mimura, S.
Sakai, and T. Kawahara, “Synthesizing waveform sequence-to-sequence to augment
training data for sequence-to-sequence speech recognition,” Acoust. Sci.
Technol., vol. 42, no. 6, pp. 333–343, 2021, doi: 10.1250/ast.42.333.
P. J. S. P. R. S. -Jasmita
Khatal, “IRJET- Real Time Image Captioning and Voice Synthesis using Neural
Network,” Irjet, vol. 8, no. 1, pp. 415–419, 2021.
H. Miyauchi, “A systematic
review on inclusive education of students with visual impairment,” Educ. Sci.,
vol. 10, no. 11, pp. 1–15, 2020, doi: 10.3390/educsci10110346.
T. Dinushika, L. Kavmini, P.
Abeyawardhana, U. Thayasivam, and S. Jayasena, “Speech Command Classification
System for Sinhala Language based on Automatic Speech Recognition,” Proc. 2019
Int. Conf. Asian Lang. Process. IALP 2019, pp. 205–210, 2019, doi:
10.1109/IALP48816.2019.9037648.