Fact · Speech recognition
12.8percent word error rate
In a 1997 review of noise experiments, a machine with noise adaptation reached 12.8 percent error at a signal-to-noise ratio of 10 dB, more than ten times the 1 percent human error rate.
Checked against its source on October 17, 2026
In the source's own words
“Even with noise adaptation, however, the 12.8% machine error rate shown in Fig. 5 at an SNR of 10 dB is more than an order of magnitude greater than the 1% human error rate.”
Speech recognition by machines and humans, Richard P. Lippmann, Speech Communication, vol. 22, pp. 1-15, 1997, Section 4 (noise experiments, Fig. 5).
Open the original- What it measures
- The noise was stationary, and its spectrum and signal-to-noise ratio were known during training. The comparison is with human listeners on the same kind of read speech.
- What it does not show
- A controlled test with steady noise at one signal-to-noise ratio. Real rooms, traffic and crowds vary in ways this does not capture.