Answers are grounded in this paper and cite their sources.
This study examined the impact of incorporating computer-assisted pronunciation training (CAPT) in a third-semester Spanish course over a 15-week period. Forty-four students were divided into two groups, one experimental (n=29) and one control (n=15). Both groups completed a pre- and post-semester recording in order to measure any improvement in their pronunciation over the duration of the study. On a near-weekly basis, the experimental group interacted with thematic iSpraak modules with automated feedback while the control group was asked to record themselves speaking in Flip/Padlet to match time on task. The control group received no feedback on their pronunciation. The pre- and post-study recordings for both groups were transcribed using MacWhisper Pro, and transcripts were subsequently processed for changes in word error rate (WER) and Levenshtein distance. Results showed a significant difference between the two groups for Levenshtein distance only, whereby the experimental group improved more than the control group.
No takes yet. Share an insight, caveat, or question.
Nickolai et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: