Guided ASR practice did not produce statistically significant improvement in any specific pronunciation error type, with some errors unimproved or regressed¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r2 · q2
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Paired t-tests on each error category showed no statistically significant improvement for any error type, though treatment-group improvements exceeded control-group changes for most categories. → Dillon 2023 q2 i? Some error types showed no improvement (Wh/F) and others showed regression (BPFV). → Dillon 2023 (2)

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 · i? · causal · r2

Per-category paired t-tests on error types (Vowel, LR, Epenthesis, MISC, BPFV, S/SH, J/CH/Z, Wh/F) in the quasi-experiment; the article states "none of the error types listed show a significant p-value" despite descriptive improvements in the treatment group.

"Second, the results of paired t tests in each category did not demonstrate statistically significant improvement. While improvements did occur, none of the error types listed show a significant p-value (which was set at >.05)."

Dillon 2023 (2)¶

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 · i? · causal · r2

Analysis of error-type changes in Table 5 of the quasi-experiment found "some pronunciation errors did not show improvement at all (Wh/F), while others showed regression (BPFV)", limiting conclusions about specific error correction.

"First, some pronunciation errors did not show improvement at all (Wh/F), while others showed regression (BPFV)."

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
• Amount of ASR practice (days per week, session length) showed no observable difference in pronunciation improvement — related
• CAPT software shows promising results for segmental pronunciation, while prosodic features and fluency still require further research and development — reports the opposite
• Explicit pronunciation instruction improves controlled production of targeted sounds and prosody, with smaller and less certain gains in spontaneous speech — reports the opposite
• Whether individual or peer practice works better with ASR-based pronunciation training is unsettled: one study found individual work best, a meta-analysis found peer practice gave larger effects — related
• Students responded positively to ASR pronunciation training and the Rainbow passage, but were mixed on technical aspects of recording and voice typing — related
• Resource scarcity and large class sizes limit individualized pronunciation feedback in Bangladeshi classrooms — related
• An AI-supported reading progress tool produced large effect sizes for speed and accuracy but not significant prosody gains for third-grade EFL learners — related
• Step-by-step automated annotations accelerated correction of procedural misconceptions, with intervention students rectifying fundamental errors weeks before control peers — related