Evaluating the scoring system of an AI-integrated app to assess foreign language phonological decoding
Evaluating the scoring system of an AI-integrated app to assess foreign language phonological decoding
Phonological decoding in a foreign language (FL)—a two-part process involving first the ability to map written symbols to their corresponding sounds and second to pronounce them intelligibly—is foundational for reading and vocabulary acquisition. Yet assessing this skill efficiently and at scale in young learners remains a persistent challenge. Here, we introduce and evaluate the accuracy and effectiveness of a novel method for assessing FL phonological decoding using an AI-driven app that automatically scores children's pronunciation of symbol-sound correspondences. In a study involving 254 learners of French and Spanish (aged 10–11) across five UK primary schools, pupils completed a read-aloud task (14 symbol-sound correspondences) that was scored by the app’s automatic speech recognition (ASR) technology. The validity of these automated scores was tested by fitting them as independent variables in regression models predicting human auditory coding. The multiple significant relationships between automated and human scores that were established indicate that there is great potential for ASR-based tools to reliably assess phonological decoding in this population. These findings provide the first large-scale empirical validation of an AI-based assessment of FL decoding in children, opening new possibilities, applicable to a range of languages being learnt, for scalable and efficient assessment.
Artificial intelligence, FL phonological decoding, FL pronunciation, FL reading, Language assessment, Young learners
Turner, James
fd6de0d7-09f9-44e7-9425-c654cccd3475
Porter, Alison
978474c5-8b0b-4dc6-8463-3fd68162d0cd
Graham, Suzanne
551397d9-58ef-41ed-b095-933019b84061
Ralph-Donaldson, Travis
fb25bb6d-735c-481a-b1b6-1fa9cd9a7715
Krüsemann, Heike
fe3b1bf3-d481-4fed-a3b7-3eec83401c52
Zhang, Pengchong
67e7ce0e-4452-4b31-a2bc-fb865dd4f764
Borthwick, Kate
34fa2da0-35c3-4302-932c-141b94aec4b4
December 2025
Turner, James
fd6de0d7-09f9-44e7-9425-c654cccd3475
Porter, Alison
978474c5-8b0b-4dc6-8463-3fd68162d0cd
Graham, Suzanne
551397d9-58ef-41ed-b095-933019b84061
Ralph-Donaldson, Travis
fb25bb6d-735c-481a-b1b6-1fa9cd9a7715
Krüsemann, Heike
fe3b1bf3-d481-4fed-a3b7-3eec83401c52
Zhang, Pengchong
67e7ce0e-4452-4b31-a2bc-fb865dd4f764
Borthwick, Kate
34fa2da0-35c3-4302-932c-141b94aec4b4
Turner, James, Porter, Alison, Graham, Suzanne, Ralph-Donaldson, Travis, Krüsemann, Heike, Zhang, Pengchong and Borthwick, Kate
(2025)
Evaluating the scoring system of an AI-integrated app to assess foreign language phonological decoding.
Research Methods in Applied Linguistics, 4 (3), [100257].
(doi:10.1016/j.rmal.2025.100257).
Abstract
Phonological decoding in a foreign language (FL)—a two-part process involving first the ability to map written symbols to their corresponding sounds and second to pronounce them intelligibly—is foundational for reading and vocabulary acquisition. Yet assessing this skill efficiently and at scale in young learners remains a persistent challenge. Here, we introduce and evaluate the accuracy and effectiveness of a novel method for assessing FL phonological decoding using an AI-driven app that automatically scores children's pronunciation of symbol-sound correspondences. In a study involving 254 learners of French and Spanish (aged 10–11) across five UK primary schools, pupils completed a read-aloud task (14 symbol-sound correspondences) that was scored by the app’s automatic speech recognition (ASR) technology. The validity of these automated scores was tested by fitting them as independent variables in regression models predicting human auditory coding. The multiple significant relationships between automated and human scores that were established indicate that there is great potential for ASR-based tools to reliably assess phonological decoding in this population. These findings provide the first large-scale empirical validation of an AI-based assessment of FL decoding in children, opening new possibilities, applicable to a range of languages being learnt, for scalable and efficient assessment.
Text
1-s2.0-S2772766125000783-main
- Version of Record
Text
Accepted Manuscript (with figures)
More information
Accepted/In Press date: 22 August 2025
e-pub ahead of print date: 1 September 2025
Published date: December 2025
Keywords:
Artificial intelligence, FL phonological decoding, FL pronunciation, FL reading, Language assessment, Young learners
Identifiers
Local EPrints ID: 505369
URI: http://eprints.soton.ac.uk/id/eprint/505369
ISSN: 2772-7661
PURE UUID: 85da26b3-4de1-45c6-aa51-bd3e474d8f20
Catalogue record
Date deposited: 07 Oct 2025 16:50
Last modified: 17 Oct 2025 01:59
Export record
Altmetrics
Contributors
Author:
James Turner
Author:
Suzanne Graham
Author:
Travis Ralph-Donaldson
Author:
Heike Krüsemann
Author:
Pengchong Zhang
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics