Fact · Voice and AI
Yang and colleagues study whether large language models can act as post-processors for speech recognition, performing rescoring and error correction on the output of a recognizer.
Checked against its source on October 17, 2026
In the source's own words
“We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction.”
Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting, Chao-Han Huck Yang et al., IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2023, 2023, Abstract.
Open the original- What it measures
- The paper is a research study. The authors place a language model after an existing recognizer and test it on two out-of-domain benchmarks, ATIS and WSJ.
- What it does not show
- A research question, not a product claim. It does not say that any commercial dictation app uses this method, and its benchmarks are not everyday dictation.