期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2016
卷号：4
期号：3
页码：3019
DOI：10.15680/IJIRCCE.2016.0403020
出版社：S&S Publications
摘要：In today's world, there exists a basic need to simplify human machine interaction as well to make the most of technologies to not only enhance the way machines learn but also how we learn. In classrooms, delivery of lectures with sound as a medium has become a clichéd process which has its own pros and cons. Due to certain constraints (like noise and dialect) students find it difficult to grasp the concepts which are bei ng taught. Thus comes into picture the need for designing a teaching assistant system which takes voice as an input . Speech recognition is the ability of a machine or software to identify words and phrases in spoken language and convert them to a machine - readable format .This paper provides an insight into existing algorithms and methods used for Speech Recognition. Our focus is on developing a framework using Hidden Markov model to obtain readable notes (documents) from speech. These documents will be br oadcast to student's personal devices over a Wireless Network. Thus students don't have to worry if they miss any important point during the lecture because it will be directly broadcast to the students present in the lecture in the form of text file
关键词：Speech Recognition (SR); Hidden Markov Model (HMM); Broadcasting
