ASR transcription serves as a diagnostic tool identifying individual learners' pronunciation errors, with function words most commonly mispronounced¶

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 · recheck by 2026: tool and model accuracy changes quickly

Subclaims¶

q2 i? ASR was able to identify the particular pronunciation errors each individual user was prone to make, suggesting diagnostic value for teachers. → Dillon 2023 q2 i? Errors with monosyllabic function words (a, the, these, its) were the most commonly mispronounced, echoing Yang (2020) on human evaluators overlooking them. → 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

Authors' interpretation in the discussion of the transcription analysis: ASR "was able to iden- tify the particular errors which each individual user was prone to make", suggesting benefit as a diagnostic tool for teachers lacking time for individual speech analysis.

"Although there was no statistically significant improvement with any partic- ular type of pronunciation error, the technology as used in this experiment was able to iden- tify the particular errors which each individual user was prone to make."

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

Error analysis of pre/post transcriptions found "errors with function words (i.e., "a," "the," "these," and "its") were the most commonly mispronounced"; the authors suggest training focus on short one-syllable commonly misspoken words.

"Our study found that errors with function words (i.e., "a," "the," "these," and "its") were the most commonly mispronounced."

Discussion¶

Related Claims¶

• Guided ASR practice did not produce statistically significant improvement in any specific pronunciation error type, with some errors unimproved or regressed — related
• An online word error rate checker correlates strongly with the study's segmental error rate measure, offering a quick pronunciation accuracy score — related
• Amount of ASR practice (days per week, session length) showed no observable difference in pronunciation improvement — related
• Guided ASR practice improves overall pronunciation accuracy of Korean EFL learners more than ordinary classroom pronunciation practice alone — related
• Students responded positively to ASR pronunciation training and the Rainbow passage, but were mixed on technical aspects of recording and voice typing — related
• Respondents anticipated using LLMs most often (23%), followed by NLP (17%), predictive AI (14%), chatbots (13%), and ASR (10%) — related
• CAPT software shows promising results for segmental pronunciation, while prosodic features and fluency still require further research and development — a broader claim this one bears on