Fact · Dictation software
In a 2008 longitudinal study on court recordings, the word error rate of a speech recognizer rose gradually as the age of elderly speakers increased.
Checked against its source on October 17, 2026
In the source's own words
“The word error rate increases gradually as the age of the elderly speakers increase”
Longitudinal study of ASR performance on ageing voices, Ravichander Vipperla et al., Interspeech 2008 (ISCA), 2008, Abstract.
Open the original- What it measures
- The authors ran a recognizer on recordings of the US Supreme Court over several years. Their recognizer was a 2008 system, and the study compared elderly voices with adult voices.
- What it does not show
- The recordings are formal court speech, and the recognizers are from 2008. The direction of the effect is informative, but the size of the error rate is out of date for current dictation apps.