Automatic Speech Recognition is known by the acronym ASR. It is an area of computing that uses Artificial Intelligence, algorithms, and machine learning with the objective of recognizing and transcribing spoken human language automatically by machine. It involves research from the fields of linguistics, computer science, and electrical engineering. For the technology to work, the computer must have a microphone. The sound is picked up by the microphone and the system identifies what is a human voice. What is said by the person is transcribed by the system, which transforms the content into commands for the machine.
There are systems that need training, when a person reads texts, and the system specifically analyses that speech, providing greater accuracy. Systems that do not use training are called “speaker-independent” systems. They use big data to do speech recognition. Speech recognition is often confused with voice recognition. While in speech recognition the goal is to discover the who, i.e., only to identify the voice of an individual user, the focus of speech recognition is the content, converting human speech from a verbal format into a written text that will be understood by the machine. Speech recognition studies began with the expansion of telephony at the end of the 19th century and beginning of the 20th century. But the biggest development in this area has come with the advance of machine learning and big data.
