Speech Recognition
Speech recognition is AI that converts spoken language into text, also called automatic speech recognition (ASR).
What is Speech Recognition?
It powers voice assistants, call-centre analytics, subtitling and dictation. Modern systems use deep learning trained on many thousands of hours of audio and can handle many languages and accents, though accuracy still varies across speakers.
How it works
Audio is converted into acoustic features and a neural network maps them to the most likely sequence of words.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions