Work

Optical Character Recognition for the International Phonetic Alphabet

Year: 2026

Type: conference-paper

Abstract: As grammar books are increasingly used as additional reference resources specifically for very low-resource languages, a significant portion comes from scans and relies on the quality of the Optical Character Recognition (OCR) tool.We focus here on a particular script used in linguistics to transcribe sounds: the International Phonetic Alphabet (IPA).We consider two data sources: actual grammar book PDFs for two languages under documentation, Japhug and Kagayanen, and a synthetically generated dataset based on Wiktionary.We compare two neural OCR frameworks, Tesseract and Calamari, and a recent large vision-language model, Qwen2.5-VL-7B,all three in an off-theshelf setting and with fine-tuning.While their zero-shot performance is relatively poor for IPA characters in general due to character set mismatch, fine-tuning with the synthetic dataset leads to notable improvements.

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.18653/v1/2026.eacl-short.19

Authors: Shu Okabe, Dejvi Zelo, Alexander Fraser

Institutions: Munich Center for Machine Learning, Technical University of Munich

Language: English

Topic: Handwritten Text Recognition Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: European Commission

OpenAlex ID: W7140092333