Skip to content

Towards Stress-Aware Sentence-Level Filipino G2P With Weakly-Supervised ByT5 Fine-Tuning

Sep 2026 · arXiv.org · Vol abs/2609.09974 · 1 citation · 27 references
Computer Science

TL;DR

It is shown that a ByT5-based model performs well at sentence-level Filipino G2P and offers strong potential for Filipino homograph disambiguation and also measures how accurately they predict stress marker position for Filipino.

Abstract

Grapheme-to-phoneme conversion (G2P) refers to the task of converting a sequence of graphemes to a corresponding sequence of phonemes. While Filipino G2P is fairly straightforward due to its shallow orthography, the inclusion of prosodic features such as stress adds a layer of complexity that requires sentence-level context instead of single-word inputs. However, sentence-level data for Filipino typically do not include phoneme transcriptions, posing a challenge for training G2P models. As such, we investigate how to obtain sentence-level phoneme data for Filipino using available data and compare the resulting models with multilingual word-level G2P as well as measure how accurately they predict stress marker position for Filipino. We propose fine-tuning a ByT5-based model, pre-trained on multilingual word-level G2P data, on three sentence-level G2P datasets annotated with an LLM-assisted pipeline guided by data from Wiktionary. This approach produces models that perform well on the G2P task, achieving at best around 0.54% PER and 2.50% CER, a significant decrease compared to base model PER at around 19.74%, on a manually-corrected test set. The model is able to correctly classify most of the main stress classes in Filipino, but struggles particularly with malumi words. We show that a ByT5-based model performs well at sentence-level Filipino G2P and offers strong potential for Filipino homograph disambiguation.

View source

Similar papers

Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data

A context-aware, segmentation-agnostic neural G2P framework that models the joint segmentation-and-reading hypothesis space, scoring paths of a discriminative conditional random field (CRF) over a dictionary-derived word lattice over a dictionary-derived word lattice is presented.

Rui Hu, Zhen Zhan, Xiao-Long Lin · 1 citation
#artificial intelligence Open access Sep 2026

Phonemizing User-Generated Text: A Benchmark, Taxonomy, and Compositional Approach

Text-to-speech systems increasingly process user-generated text (UGT) such as ppl and imo, whose pronunciation must be inferred from the canonical rather than surface form. We introduce UGTPhon, the first grapheme-to-phoneme (G2P) benchmark for UGT in English, Vietnamese, and Korean, together with an inference-grounded...

Minju Jeon, Youngha Park, Han Sung Park et al. · 0 citations
#natural language process... Open access Oct 2026

HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR

Experimental results demonstrate that the cascaded system remains more reliable under the MLC-SLM Task 1 conditions, while unified speech LLMs offer a promising direction for future speaker-attributed ASR.

Takanori Ashihara, Kohei Matsuura, M. Mimura · 0 citations
Open access Oct 2026

Fine-Tuning Transformer Models for Indonesian Text Summarization and Translation: A Comparative Study of PEGASUS, T5, and Komodo-7B

Bahasa Indonesia ranks among the most widely spoken languages in the world. However, Natural Language Processing (NLP) research for this language remains relatively limited. This study evaluates the effectiveness of three Transformer-based models namely PEGASUS, T5, and Komodo-7B on two Indonesian-language NLP tasks: t...

Muhamad Irkham Khudzifa Al Rody · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.