Skip to content
BENIBIX Learn

Speech-to-Text (Speech Recognition)

AI🎨 MultimodalSpeech and Audio

Also known as Speech-to-Text, Speech Recognition, Automatic Speech Recognition, ASR, Transcription

AI that listens to speech and writes the words down.

Think of it like

It is like a friend who writes down every word you say. You talk, they type.

Example

Jack records a one-hour team meeting. In a few minutes, speech-to-text turns it into a written record, with each speaker marked. Then he searches it for the word 'budget'.

Why it matters

Spoken words become text you can search and quote. It also opens up sound and video to people who cannot hear.

Definition

Speech-to-text is AI that turns spoken words into written text. The model listens to the sound, cuts it into tiny slices, and works out which words were most likely said. Today's models learn from many thousands of hours of speech, so they cope with accents and some noise. Many also add commas and full stops, mark who is speaking, and give each word a time. Quality is often scored by word error rate, the share of words it gets wrong.
A sound wave goes in, and written words with times beside them come out.

Common mistake

Trusting names and numbers without a check. These are the words a model most often gets wrong.

Key takeaways

  1. 1
    Sound in. Words out.
  2. 2
    Trained on speech. Thousands of hours.
  3. 3
    Word error rate. The usual score.

Compare

Learn it properly