SPEECH RECOGNITION SYSTEM

Abstract

Speech recognition, also known as automatic speech recognition (ASR), computer speech recognition, or speech-to-text, is a capability which enables a program to process human speech into a written format. While it's commonly confused with voice recognition, speech recognition focuses on the translation of speech from a verbal format to a text one whereas voice recognition just seeks to identify an individual user's voice. Speech recognition applications are becoming more and more useful nowadays. Various interactive speech aware applications are available in the market. But they are usually meant for and executed on the traditional general-purpose computers. With growth in the needs for embedded computing and the demand for emerging embedded platforms, it is required that the speech recognition systems (SRS) are available on them too. Speech recognition systems emerge as efficient alternatives for such devices where typing becomes difficult attributed to their small screen limitations. The paper aims to test a speech recognition system that can be used for a human-machine interaction through speech. The goal is to allow the machine to recognize a set of instructions sent by the user through the voice signal. An automatic speech recognition system will be tested in order to identify words that belong to a limited vocabulary. It will be implemented by engaging a deep neural network (DNN). The construction of the network will be done with the help of the Tensorflow library, which provides support for the development of artificial intelligence algorithms. The system will be tested out on a non-homogeneous group of people, because it is desirable to develop a voice recognition system, independent of the speaker.