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¶

Claim · All claims
Evidence · 2 studies · 1 quant-synthesis r2, 1 design r1 · q2–q3 · i2 medium · n=15 studies (38 effect sizes)
Currency · newest study 2024 · 1 of 2 entries checked against their sources (automated) · not reviewed by a person

Subclaims¶

q2 i? In Elimat and Abuseileek's (2014) study of third-grade English learners using the 'Tell me more performance' program, the group of students who worked individually with the ASR system obtained the best results. → Ali 2016 q3 i2 Across 15 ASR studies with ESL/EFL learners, practising alone gave a smaller pooled effect (g = 0.44, 11 studies) than practising with a peer (g = 0.89, 5 studies), though neither confidence interval excludes zero. → Ngo et al. 2024

Evidence¶

Ali 2016¶

Ali, S. (2016). Towards the development of a comprehensive pedagogical framework for pronunciation training based on adapted automatic speech recognition systems. In S. Papadima-Sophocleous, L. Bradley & S. Thouësny (Eds), CALL communities and culture – short papers from EUROCALL 2016 (pp. 7-13). Research-publishing.net. https://doi.org/10.14705/rpnet.2016.eurocall2016.530

q2 · i? · design · r1

The article reports, citing Elimat and Abuseileek (2014), a study testing ASR efficacy with third-grade English learners across individual, pair and group work conditions, in which "The best results were obtained with the group of students who worked individually with the ASR system." No effect size is printed.

"Elimat and Abuseileek (2014) use the ‘Tell me more performance’ program to test the efficacy of ASR systems as well as various teaching techniques (i.e. individual work, pair work, group work) to train third grade learners of English. The best results were obtained with the group of students who worked individually with the ASR system."

Ngo et al. 2024¶

Ngo, T. T.-N., Chen, H. H.-J., & Lai, K. K.-W. (2024). The effectiveness of automatic speech recognition in ESL/EFL pronunciation: A meta-analysis. ReCALL, 36(1), 4–21. doi:10.1017/S0958344023000113

q3 · meta-analysis (three-level, random effects) · i2 · medium effect, g=0.69 · n=15 studies (38 effect sizes) · quant-synthesis · r2

A meta-analysis of 15 studies (2008–2021, 38 effect sizes) comparing ESL/EFL learners who practised pronunciation with automatic speech recognition (ASR) against a non-ASR condition. The pooled effect was g = 0.69 (95% CI 0.31 to 1.08), with substantial heterogeneity (Q = 227.70; I² 56.56% between studies). The authors did not test for publication bias, and name the small number of primary studies as the main limitation. Read from the publisher's open-access full text; the article was published online in 2023. By learning activity, practising with ASR alone gave g = 0.44 (11 studies, 95% CI −1.13 to 2.01), with a peer g = 0.89 (5 studies, 95% CI −0.69 to 2.48), and with a teacher g = 1.24 (2 studies). The authors recommend peer activities, citing Elimat & AbuSeileek (2014) among others, and advise caution with young children, who may be distracted by group members. This bears against the claim for ESL/EFL learners in general.

"The pooled effect size was medium (g = 0.69), and the confidence interval was not across zero (95% CI = [0.31, 1.08])."

Discussion¶

Ngo et al. (2024) point the other way from this claim: across ASR studies, practising alone produced the smallest pooled effect and practising with a peer or teacher larger ones, although every learning-activity estimate has a confidence interval that crosses zero. Elimat & AbuSeileek (2014), the study this claim reports through Ali (2016), is in Ngo et al.'s sample, and Ngo et al. cite it both for peer groups of about four and for caution with young children. The claim's finding may therefore hold for third-grade learners but is not what the pooled evidence across ESL/EFL learners shows.

Related Claims¶

• Guided ASR practice improves overall pronunciation accuracy of Korean EFL learners more than ordinary classroom pronunciation practice alone — related
• CAPT software shows promising results for segmental pronunciation, while prosodic features and fluency still require further research and development — related
• The Fluspeak ASR-based pronunciation software gave good results with beginners focusing on phoneme production but poor results overall for advanced learners seeking fluency — related
• Guided ASR practice did not produce statistically significant improvement in any specific pronunciation error type, with some errors unimproved or regressed — related
• Students responded positively to ASR pronunciation training and the Rainbow passage, but were mixed on technical aspects of recording and voice typing — related
• Research at primary and secondary levels indicates students learn more through non-competitive collaborative group work than in individualized competitive classrooms — related
• In this inquiry, student pairs work better than groups of three because larger groups risk disengaging members — related
• Positive attitudes towards English and high motivation are associated with better pronunciation outcomes — related
• Overall CPSE did not differ significantly between individual programming and RTC-based collaborative programming — related