Peer-reviewed research

Improving the user interface of dictation software

Ben Kraal et al., Proceedings of the 9th Australian International Conference on Speech Science and Technology, Melbourne, 2002, 2002

Read on October 16, 2026

What it is: A conference paper from the University of Canberra that argues novice dictation users keep correcting errors by voice because they carry over habits from typing. It reviews earlier observational studies of how users correct dictation errors over time.
How much weight it carries: Accepted after full review by the conference. It is a short design paper that summarizes earlier research, so the 20-hour finding is quoted from an earlier study (Horn et al. 2000) and is not a new measurement. The original study should be checked before relying on the exact number.

Facts taken from this source

Citing an earlier study, Kraal and colleagues report that users who keep dictating for about 20 hours start to combine voice correction with keyboard and mouse correction.
“subjects who use dictation software for an extended period of time (about 20 hours) tend to augment spoken correction with multimodal correction” (Literature review (body text))
Kraal and colleagues say novice dictation users keep correcting errors by voice, which shows an incorrect mental model of dictation.
“The tendency of novice users to persist with spoken error correction illustrates that novices have an incorrect mental model of dictation” (Abstract)

Peer-reviewed research

Ben Kraal et al., Proceedings of the 9th Australian International Conference on Speech Science and Technology, Melbourne, 2002, 2002

Read on October 16, 2026

What it is: A conference paper from the University of Canberra that argues novice dictation users keep correcting errors by voice because they carry over habits from typing. It reviews earlier observational studies of how users correct dictation errors over time.
How much weight it carries: Accepted after full review by the conference. It is a short design paper that summarizes earlier research, so the 20-hour finding is quoted from an earlier study (Horn et al. 2000) and is not a new measurement. The original study should be checked before relying on the exact number.

Citing an earlier study, Kraal and colleagues report that users who keep dictating for about 20 hours start to combine voice correction with keyboard and mouse correction.
“subjects who use dictation software for an extended period of time (about 20 hours) tend to augment spoken correction with multimodal correction” (Literature review (body text))
Kraal and colleagues say novice dictation users keep correcting errors by voice, which shows an incorrect mental model of dictation.
“The tendency of novice users to persist with spoken error correction illustrates that novices have an incorrect mental model of dictation” (Abstract)