EMNLP Findings2025
Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Models
Mahta Fetrat Qharabagh, Zahra Dehghanian, Hamid R. Rabiee
Abstract
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 Ho-moRich dataset generated through this pipeline, and demonstrate its effectiveness by applying it to enhance a state-of-the-art deep learningbased G2P system for Persian. Second, we advocate for a paradigm shift-utilizing rich offline datasets to inform the development of fast, statistical methods suitable for latencysensitive 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, Ho-moFast eSpeak. Our results show an approximate 30 percentage-point improvement in homograph disambiguation accuracy for the deep learning-based and eSpeak systems.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on2
Related papers
- Deepfake Defense: Constructing and Evaluating a Specialized Urdu Deepfake Audio DatasetSheza Munir, Wassay Sajjad, Mukeet Raza, Emaan Abbas et al.ACL Findings 2024 · 7 citations
- Enhancing Chinese Offensive Language Detection with Homophonic PerturbationJunqi Wu, Shujie Ji, Kang Zhong, Huiling Peng et al.EMNLP 2025
- A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics RestorationAvi Shmidman, Joshua Guedalia, Shaltiel Shmidman, Moshe Koppel et al.EMNLP Findings 2020 · 3 citations
- Spanning the Spectrum of Hatred Detection: A Persian Multi-Label Hate Speech Dataset with Annotator RationalesZahra Delbari, Nafise Sadat Moosavi, Mohammad Taher PilehvarAAAI 2024 · 11 citations
- CIEASR: Contextual Image-Enhanced Automatic Speech Recognition for Improved Homophone DiscriminationZiyi Wang, Yiming Rong, Deyang Jiang, Haoran Wu et al.ACM MM 2024
