Fact · Speech recognition
Inverse text normalization converts the spoken-domain output of a speech recognizer into written-domain text, to make the recognizer's output easier to read.
Checked against its source on October 17, 2026
In the source's own words
“Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output.”
NeMo Inverse Text Normalization: From Development To Production, Yang Zhang et al., arXiv, 2021, Abstract.
Open the original (DOI 10.48550/arXiv.2104.05055)- What it measures
- The NVIDIA NeMo team defines the task in the first sentence of the paper's abstract. The paper is about a rule-based library for English that can be extended to other languages.
- What it does not show
- A definition from one research group's paper. The examples of what counts as written form are not in the abstract, so the glossary entry gives its own illustrations.