Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data
cs.CL
Submitted: 2026-09-17
Updated: 2026-09-21
Comments: Submitted to ICASSP 2027
Code: https://github.com/Parakeet-Inc/Joyo-Kanji-Yomi-Benchmark-Parakeet-Edition
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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 neural G2P method that scores paths of a discriminative conditional random field (CRF) over a word lattice constructed from dictionaries. To tackle data scarcity, we utilize large language models (LLMs) to generate more than 2 million sentences. Experimental results demonstrate that our method strongly 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.
Sources
- Benchmarking Large Language Models for Grapheme-to-Phoneme Conversion: A Japanese Case Study
- Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
- Qwen3-TTS Technical Report
- OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
- CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training
- TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch
- g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
- Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
- Qwen3 Technical Report
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering