Virtual Booth

Abstract

This systematic review synthesizes current evidence on the use of voice recognition tools to support pronunciation and reading fluency in early childhood education (ECE). Adopting the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology, a total of 38 peer-reviewed studies published between 2020 and 2025 were identified across databases such as Scopus, ERIC, and Web of Science. The analysis reveals that voice recognition technologies—ranging from automated speech feedback applications to AI-integrated literacy platforms—are increasingly used to scaffold phonemic awareness, articulation, and reading fluency among young learners. Tools with real-time corrective feedback, gamified interaction, and adaptive pronunciation modelling demonstrated higher engagement and learning gains. The findings are mapped to the Malaysian Qualifications Framework (MQF 2.0), particularly under the Cognitive (Cluster 2), Digital Skills (Cluster 5), and Communication Skills (Cluster 4) domains. This review offers valuable insights for researchers, instructional designers, and policymakers seeking to integrate evidence-based digital interventions into ECE literacy practices, aligned with the broader aims of values-based education and sustainable competencies.