Diacritic Recognition Performance in Arabic ASR

TL;DR

This paper evaluates how diacritic recognition affects Arabic ASR performance, showing that integrating diacritics during training improves recognition accuracy more than post-processing diacritization.

Contribution

It provides a systematic analysis of diacritic recognition in Arabic ASR, comparing input diacritization effects and demonstrating the benefits of manual diacritization during model fine-tuning.

Findings

ASR diacritization outperforms text-based diacritization in post-processing.

Manual diacritization during fine-tuning improves diacritic recognition.

Diacritic recognition can be isolated from overall ASR performance using specific metrics.

Abstract

We present an analysis of diacritic recognition performance in Arabic Automatic Speech Recognition (ASR) systems. As most existing Arabic speech corpora do not contain all diacritical marks, which represent short vowels and other phonetic information in Arabic script, current state-of-the-art ASR models do not produce full diacritization in their output. Automatic text-based diacritization has previously been employed both as a pre-processing step to train diacritized ASR, or as a post-processing step to diacritize the resulting ASR hypotheses. It is generally believed that input diacritization degrades ASR performance, but no systematic evaluation of ASR diacritization performance, independent of ASR performance, has been conducted to date. In this paper, we attempt to experimentally clarify whether input diacritiztation indeed degrades ASR quality, and to compare the diacritic recognition performance against text-based diacritization as a post-processing step. We start with pre-trained Arabic ASR models and fine-tune them on transcribed speech data with different diacritization conditions: manual, automatic, and no diacritization. We isolate diacritic recognition performance from the overall ASR performance using coverage and precision metrics. We find that ASR diacritization significantly outperforms text-based diacritization in post-processing, particularly when the ASR model is fine-tuned with manually diacritized transcripts.