Automatic Prediction of Child Speech Fluency with Game-Based Data from German Preschoolers

Valentin Kany, Bernd Möbius, Jürgen Trouvain


Abstract
This paper introduces an approach to automatically predict the speech fluency of preschool children as part of Language Proficiency Assessments. We use spontaneous speech data from children with German as native and second language aged 4–6 years, collected via a game–based elicitation method. The recordings were mainly annotated manually on various fluency-related phenomena. The resulting feature values were compared to human fluency ratings of the same data. The human ratings and the fluency-related acoustic features were used to build Cumulative Link Mixed Models (CLMMs) with and without splines to test their ability to predict the human ratings with multiple metrics (Spearman’s ρ, MAE, quadratic weighted κ). Results show that a parsimonious linear model already reaches near-human agreement (quadratic weighted kappa κ = 0.65) and that incorporating non-linear spline effects does not improve predictive accuracy. These findings suggest that relatively simple CLMMs can substitute additional human raters in fine-grained fluency assessment of preschool children, which is a task that is already challenging for trained listeners.
Anthology ID:
2026.lrec-1.439
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
5607–5616
Language:
External URL:
https://lrec.elra.info/lrec2026-main-439
DOI:
10.63317/48vj8xeqn5ok
Bibkey:
Cite (ACL):
Valentin Kany, Bernd Möbius, and Jürgen Trouvain. 2026. Automatic Prediction of Child Speech Fluency with Game-Based Data from German Preschoolers. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5607–5616, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Automatic Prediction of Child Speech Fluency with Game-Based Data from German Preschoolers (Kany et al., LREC 2026)
Copy Citation: