Automatic Speech Recognition (ASR), or simply Speech Recognition, is focused on transforming a sequence of sound waves into a string of letters or words, and as such is considered to be a component of Natural Language Understanding (NLU). A part of Natural Language Processing (NLP), speech recognition provides the ability to identify the words, structure, intent, and speech components of spoken language. Speech recognition is used as a component of speech-to-text as well as higher level functions for applications such as chatbots and voice assistants. The terms Automatic Speech Recognition (ASR), Speech Recognition, and Speech-to-Text (STT) are often used interchangeably.
Glossary of Artificial Intelligence (AI), Machine Learning (ML), and Big Data Terms
Automatic Speech Recognition (or simply Speech Recognition)
