Automatic Speech Recognition (ASR) is technology or software that automatically converts spoken language into text, which can be done in real-time.
While ASR may seem convenient to implement and use, along with being free or low-cost, the accuracy of ASR tools vary. This is the main reason why ASR is not considered effective communication.
ASR should not be used in lieu of real-time speech-to-text services, but can be beneficial in specific situations, such as:
A stop-gap tool for one-on-one situations when deaf and hearing people need to communicate.
A place to start when creating transcripts or captioning produced videos. Editing ASR transcripts can be more efficient than creating a transcript from scratch.
An accommodation for people with mobility and/or dexterity disabilities to type independently.
As a note-taking tool for some students.