Alam, Md. Golam RabiulReza, Md. TanzimIqbal, Syed BayesRifat, Riazul IslamHussain, Md AkifBiswas, Simon2022-12-122022-12-1220222022-05ID: 18101198ID: 18101236ID: 18101073ID: 18101543http://hdl.handle.net/10361/17636Cataloged from PDF version of thesis.Includes bibliographical references (pages 24-25).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.From the very beginning of the 20th century, there has been a significant devel opment in the education system using modern technology. However, this rapid development has very little scope to facilitate the education system for the people without sight. Though braille is a method for sight disabled people it has not been incorporated that much with the modern education system. On the other hand, many papers and works have been done on it but a maximum of these is about the conversion of a text character to a braille pattern with considerable accuracy so far no work has been done that can work with voice to convert a character into braille pattern for Bangla language. This paper introduces a development that will help the visually impaired people to start their very basic education with a technology that is capable of recognizing a Bangla character uttered by a person and can convert that character into braille pattern so that using a finger touch one can recognize the cor responding braille for that character. This voice recognition will be done using the Visual Geometry Group (VGG-16) model of Convolutional Neural Network (CNN) and Arduino Uno, LCD 16x4 display will be used to generate the braille pattern for the recognized character. The model is trained with 50 epochs and we achieved 98% of train accuracy and after evaluating test data we gained 92.42% test accuracy.25 Pagesen-USBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Convolutional neural network(CNN)BrailleSpectrogramClassificationVGG-16Arduino UnoLCD 16x4 displayMachine LearningComputer algorithmsCognitive learning theory (Deep learning)Thesis