Voice Assistant for Ubuntu Implementation Using Deep Neural Network

Abstract

Speech recognition is an area of artificial intelligence. It is a technique which identifies words spoken by human and converts them into machine understandable format [1,2]. Speech recognition systems require "training" which includes contains audio waves and its text. There are also systems which do not require training, and such systems are called as speaker-independent systems [2]. Speech recognition has benefited from deep learning and big data. Many systems have introduced in the literature [2]. Such systems will need only a part of natural language processing, i.e., automatic speech recognition (ASR).Acoustic modeling and language modeling are important parts of modern statistically based speech recognition algorithms [2]. Hidden Markov model (HMM) is widely used in many systems [3]. Earlier dynamic time warping was used but then was replaced by HMM. Then, neural networks emerged as an attractive acoustic modeling approach in ASR. Since then Neural Networks are used mostly. There are many applications of speech recognition like healthcare, car systems, military, telephony, people with disabilities, aerospace, hands-free computing and many more.