Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment

TL;DR

Harf-Speech is a new modular system for Arabic phoneme-level speech assessment that achieves high correlation with expert scores and outperforms existing methods.

Contribution

It introduces a clinically aligned, interpretable framework for Arabic pronunciation assessment combining phoneme scoring, fine-tuned models, and validation against expert judgments.

Findings

Best model achieves 8.92% phoneme error rate.

Harf-Speech correlates with expert scores at 0.791 Pearson.

Outperforms existing assessment frameworks.

Abstract

Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92\% phoneme error rate. Three certified speech-language pathologists independently scored 40 utterances for clinical validation. Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks. These results show Harf-Speech yields clinically aligned, interpretable scores comparable to inter-rater expert agreement.