Automatic Speech Recognition

2

Automatic Speech Recognition (ASR) is the process of converting spoken words into text. ASR is a subset of speech recognition, which is the broader term for both recognition and transcription. ASR has been used since the 1960s and was a popular research topic for many years. It became more widely used in the 1990s with the advent of low-cost digital signal processing, faster computers, and better algorithms for word recognition. The first ASR programs were mainly developed to aid people who had trouble speaking due to physical disabilities, but nowadays it is used in many other applications such as call centers or other customer service lines.