Fact · Speech recognition
The third-edition draft of Jurafsky and Martin's textbook says the input to a speech recognizer is a series of acoustic waves.
Checked against its source on October 17, 2026
In the source's own words
“The input to a speech recognizer is a series of acoustic waves”
Speech and Language Processing, Chapter 16: Automatic Speech Recognition (draft), Daniel Jurafsky and James H. Martin, Stanford University, online manuscript of the third edition, 2026, Chapter 16, automatic speech recognition.
Open the original- What it measures
- A standard textbook definition of the input side of automatic speech recognition, from the chapter on the topic.
- What it does not show
- Describes the task in general. It does not say which architecture a product uses.