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.
Abstract
Grapheme-to-phoneme (G2P) conversion turns raw text into its phonemic form and is an essential part of both text-to-speech (TTS) and automatic speech recognition (ASR) systems. It is required to be fast, stable and context-aware. For unsegmented languages such as Japanese, G2P additionally couples word segmentation with highly context-dependent polyphone disambiguation, and the scarcity of accurately annotated data remains a bottleneck. In this paper, we present 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. To tackle data scarcity, we utilize large language models (LLMs) to generate more than 2 million sentences. Experimental results demonstrate that our method substantially outperforms conventional morphological analyzer-based methods and neural sequence models. On the Joyo-Kanji-Yomi benchmark, our method reaches 99.62% target word reading accuracy, 0.32% target word phoneme error rate (PER) and 0.14% sentence PER.
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.
Lorenz Bernard Marqueses, P. Silva, Chastine Cabatay et al.· arXiv.org· 1 citation
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.· Conference on Empirical Meth...· 0 citations
A training-free ST2P pipeline that integrates both lexical and acoustic information at inference time is proposed that outperforms all baselines, including a trained ST2P model and commercial multimodal LLMs.
Hikaru Asano, Yotaro Kubo, So Kuroki· arXiv.org· 0 citations
FastThaiG2P provides sub-millisecond Thai grapheme-to-phoneme conversion for text-to-speech pipelines (International Phonetic Alphabet and Kokoro-TTS conventions) using a PyThaiNLP-tokenized, extensible dictionary and normalization rules for common Central Thai speech. The approach achieves an average latency of 0.15 m...
Text-to-speech models for Bantu tonal languages are challenged by a tonal system that is rooted in both the lexis (i.e., the inventory of words, stems, and affixes) and the grammar (i.e., morpho-syntax). To complicate matters, the standard writing systems of these languages often omit tone markings and syllable duratio...
This paper addresses the task of automatic identification of German word forms and constructs an end-to-end model framework based on deep neural networks that employs character-level and subword-level dual-channel feature representations, and combines encoder-decoder architecture, scaled dot-product attention, and posi...
Bo Wang· International Conference on...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.