SPEECH RECOGNITION USING DEEP LEARNING

Abstract

Speech is the way of communicating with others, by which we can understand each other’s thoughts and there fully. Speech recognition that's associate lay to rest disciplinary field of linguistics aids in developing technologies that empowers the recognition and translation of speech into text. The most crucial information is taken from a text source and adequately summarized by text summarization. In this we talked about the algorithm we used and how its implemented, step by step and Input as well output in the implementation and result section Text account extracts the utmost very important information from a provide that would be a text. In our paper we focus on processing the vocal data received from the microphone as input. Initially we process the voice information and extract only the necessary voice eliminating all the unnecessary or noise data. Finally, we convert the extracted voice data into the text format. We apply the deep learning concepts to make our model work efficiently. The output depends upon the quality of input received from the microphone.