Rahman, Mohammad ZahidurIslam, SamiulHaque, Kazi InjamamulSaha, UllashBiswas, SudiptoBillah, Md. MuhtasimMomin, Abu Saleh Al2017-11-222017-11-2220162016ID 13101103ID 13101156ID 13101159ID 13101167ID 13101220http://hdl.handle.net/10361/8529Cataloged from PDF version of thesis report.Includes bibliographical references (pages 49-51).This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2016.Natural language processing and speech to text can make a significant improve in medical dictation (transcription, radiology report, prescription etc) in a developing country like Bangladesh. In the field of telemedicine it can play a very crucial part in the absence of qualified doctors and specialists to prescribe medicine and provide with medical support in remote and rural places. This paper is based on a real time speech detection with a standalone system to implement it in a single board computer Raspberry PI that can also work in crowded place. The recognition engine used for the system is JULIUS along with the toolkit HTK to manipulate HMM(Hidden Markov Model). The acoustic model is set to such a way that it can detect selected medicine names those are widely used in Bangladesh. The accuracy rate of our trained dictionary is 84% but a silent environment and longer string prodeces 94% accuraccy which can also be imroved with more accurate training with advanced directional microphone. The intention of implementing the system in Raspberry PI was to have a future innovation of a standalone device for medical dictation and telepharmacy.72 pagesenBRAC University thesis 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.Raspberry PIMedical dictationNatural languageTelepharmacyThesis