K-Function: Joint Pronunciation Transcription and Feedback for Evaluating Kids Language Function

TL;DR

K-Function is a novel framework that combines phoneme-level transcription with LLM-based scoring to evaluate young children's language skills accurately, addressing challenges posed by child speech variability.

Contribution

It introduces K-WFST, a phoneme encoder with a similarity model, achieving low error rates and enabling effective LLM-driven assessment of children's language development.

Findings

Achieved 1.39% phoneme error rate on MyST dataset

Enabled LLM-based scoring that aligns with human evaluations

Improves scalability of language screening for children

Abstract

Evaluating young children's language is challenging for automatic speech recognizers due to high-pitched voices, prolonged sounds, and limited data. We introduce K-Function, a framework that combines accurate sub-word transcription with objective, Large Language Model (LLM)-driven scoring. Its core, Kids-Weighted Finite State Transducer (K-WFST), merges an acoustic phoneme encoder with a phoneme-similarity model to capture child-specific speech errors while remaining fully interpretable. K-WFST achieves a 1.39 % phoneme error rate on MyST and 8.61 % on Multitudes-an absolute improvement of 10.47 % and 7.06 % over a greedy-search decoder. These high-quality transcripts are used by an LLM to grade verbal skills, developmental milestones, reading, and comprehension, with results that align closely with human evaluators. Our findings show that precise phoneme recognition is essential for creating an effective assessment framework, enabling scalable language screening for children.