Peer-reviewed research
From User Perceptions to Technical Improvement: Enabling People Who Stutter to Better Use Speech Recognition
Colin Lea et al., Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (arXiv preprint), 2023 · DOI 10.48550/arXiv.2302.09044
Read the originalRead on October 16, 2026
- What it is
- An Apple research paper presented at CHI 2023. It combines a survey of 61 people who stutter, recordings of voice assistant commands and dictation from 91 people who stutter, and technical changes to a consumer speech recognizer that reduce cut-offs and word errors.
- How much weight it carries
- Peer-reviewed at ACM CHI, a top human-computer interaction venue. Written by Apple researchers about Apple's own recognizer, so the numbers describe one commercial system and a research prototype, not every dictation engine.
Facts taken from this source
- In Apple research with 91 people who stutter, technical changes to a consumer speech recognizer cut utterances off 79.1 percent less often and improved word error rate from 25.4 percent to 9.9 percent.
“Through three technical investigations, we demonstrate how many common errors can be prevented, resulting in a system that cuts utterances of 79.1% less often and improves word error rate from 25.4% to 9.9%.” (Abstract)