An online word error rate checker correlates strongly with the study's segmental error rate measure, offering a quick pronunciation accuracy score¶

Claim · All claims
Evidence · 1 study · causal r2 · q2 · i3 large
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person · recheck by 2026: tool and model accuracy changes quickly

Subclaims¶

q2 i3 SER scores correlated with an online word error rate tool at Pearson's correlation of .788 (r = .788), supporting the WER tool as a reliable quick measure of pronunciation accuracy. → Dillon 2023

Evidence¶

Dillon 2023¶

Dillon, Thomas, & Wells, Donald. (2023). Effects of pronunciation training using automatic speech recognition on pronunciation accuracy of Korean English language learners. English Teaching, 78(1), 3-23. https://doi.org/10.15858/engtea.78.1.202303.3

q2 · i3 · causal · r2

Correlational validation analysis of the segmental error rate against an online word error rate checker produced "a reasonably strong Pearson's correlation of .788" (r = .788); the authors suggest the WER tool could let students self-assess progress quickly.

"As a hedge against researcher bias, the results generated according to the SER were correlated against scores generated by an online word error rate checker via https://www.am-berscript.com/en/wer-tool, which resulted in a reasonably strong Pearson's correlation of .788."

Discussion¶

Related Claims¶

• ASR transcription serves as a diagnostic tool identifying individual learners' pronunciation errors, with function words most commonly mispronounced — related
• Guided ASR practice improves overall pronunciation accuracy of Korean EFL learners more than ordinary classroom pronunciation practice alone — related