Xeinabot: A Spoken Intelligent Agent approach Using Hidden Markov Model with Chatbot Technology in Android Environmen

Abstract

The present study describes the designing and its execution of xeinabot, a public domains spoken smart agent in an Android system. The primary goal of this work is to design and construct a personal agent that combines chatbot technology and statistical methods for speech search. The former uses Hidden Markove System Algorithmic procedures and the N-gram technique for Automatically Speech Recognition, while the latter relies on chatbot systems for Speech Recognizing and uses Multinomial Naïve Bays Method for classification and brute force search for matching patterns. The main objective of this strategy is to create an agent that convinces people into thinking they are speaking with a human when, in reality, they are speaking with a machine. utilizing chatbot technology to make advantage.   After evaluating roughly 500 phrases on various subjects, the evaluation findings show very good results and, in the majority of circumstances, the agent behaves like a person. The success task (correct voice recognition and speech understanding) amounts to 86.6%.