automatic speech recognition

American  

[aw-tuh-mat-ik speech rek-uhg-nish-uhn] / ˈɔ təˌmæt ɪk ˈspitʃ ˌrɛk əgˈnɪʃ ən /

noun

Digital Technology.

1. an algorithmic analysis of spoken language that uses machine learning and artificial intelligence to convert human spoken input into digital output, like text, or to interpret voiced commands, like those directed to a virtual assistant. ASR

---

Etymology

Origin of automatic speech recognition

First recorded in 1955–60

Example Sentences

To reach this conclusion, scientists used automatic speech recognition techniques and analyzed recordings from the Animal Sound Archive at the Berlin Natural History Museum.

From Science Daily • Feb. 11, 2026

In late 2022, the maker of ChatGPT started giving away unfettered acccess to its automatic speech recognition model called Whisper, trained on 680,000 hours of multilingual data.

From Los Angeles Times • Jan. 29, 2026

Alexa uses a range of A.I. techniques, including automatic speech recognition.

From New York Times • Jun. 8, 2023

Others, like Otter and Live Transcribe, instead rely on what’s called automatic speech recognition, which uses artificial intelligence to learn and capture speech.

From Seattle Times • Jun. 27, 2022

In a couple of papers on automatic speech recognition, Google engineers report that their projects’ training data comes from millions of Google voice-search and dictation clips, representing tens of thousands of hours of speech.

From Slate • Oct. 25, 2019