84

Artificial Intelligence Research Areas

The working domain of artificial intelligence is huge in width and breadth. Therefore before proceeding further considers the prospering and common research areas in the domain of artificial intelligence are:-

• Expert System – In artificial intelligence, an expert system are used for solving complex problems by reasoning about knowledge, represented primarily by if-then rules rather than by conventional procedural code. In general, an expert system is a computer system that uses the decision-making capability of a human expert.
• Neural Networks – Neural networks are system of interconnected ?neurons? which exchange messages between each other. In machine learning artificial neural networks (ANNs) belongs to a family of model inspired by biological neural networks (the nervous system of animals, present inside a brain) and are used for approximate functions or estimate a large number of inputs which are generally unknown.
• Robotics – Robotics is a branch of Artificial Intelligence (AI), it is mainly composed of electrical engineering, mechanical engineering and computer science engineering for construction, designing and application of robots. Robotics is science of building or designing an application of robots. The aim of robotics is to design an efficient robot.
• Fuzzy logic – Fuzzy logic was introduced in 1965 as a proposal of fuzzy set theory. It is applied to various fields, from artificial intelligence to control theory. Fuzzy logic is a form of many-valued logic in which truth table values of variable may be real number between 0 and 1.
• Natural Language Processing – Natural language processing (NLP) is a method of communicating with an intelligent system by using a natural language such as English. The input and output of NLP system is speech and written text.

---

Voice and Speech Recognition

Voice and Speech both terms are common in expert systems, natural language processing and robotics. As these terms are used interchangeably, their objectives are different.

The differences between voice and speech recognition are given below:

Voice Recognition	Speech Recognition
The aim of voice recognition is to recognize WHO is speaking.	The aim of speech recognition is to understand and comprehend WHAT was spoken.
This recognition system requires training as it is person oriented.	This recognition system does not require training as it is not speaker dependent.
It is used for identifying a person by analyzing its voice, tone, pitch, and accent, etc.	It is used for hand-free computing, menu navigation, or map.
Speaker dependent Voice Recognition systems are easy to develop.	Speaker independent Speech Recognition systems are difficult to develop.