Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models
This addresses the challenge of real-time accessibility tools like screen readers for low-resource languages, though it is incremental as it builds on existing methods like eSpeak.
The paper tackled homograph disambiguation in grapheme-to-phoneme conversion by proposing a semi-automated pipeline to create the HomoRich dataset and developing a fast rule-based system, HomoFast eSpeak, resulting in an approximate 30% improvement in accuracy for both deep learning and eSpeak systems.
Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is labor-intensive and costly, and (2) specific disambiguation strategies introduce additional latency, making them unsuitable for real-time applications such as screen readers and other accessibility tools. In this paper, we address both issues. First, we propose a semi-automated pipeline for constructing homograph-focused datasets, introduce the HomoRich dataset generated through this pipeline, and demonstrate its effectiveness by applying it to enhance a state-of-the-art deep learning-based G2P system for Persian. Second, we advocate for a paradigm shift - utilizing rich offline datasets to inform the development of fast, rule-based methods suitable for latency-sensitive accessibility applications like screen readers. To this end, we improve one of the most well-known rule-based G2P systems, eSpeak, into a fast homograph-aware version, HomoFast eSpeak. Our results show an approximate 30% improvement in homograph disambiguation accuracy for the deep learning-based and eSpeak systems.