The paper introduces a context‑aware neural grapheme‑to‑phoneme (G2P) system for unsegmented languages like Japanese, using a discriminative conditional random field over a word lattice built from dictionaries. It addresses data scarcity by generating over two million sentences with large language models. Experiments show the method surpasses traditional morphological analyzers and neural sequence models, achieving 99.62% target word reading accuracy and very low phoneme error rates on the Joyo‑Kanji‑Yomi benchmark.
By Rui Hu, Zhenpeng Zhan, Xiaolong Lin
arXiv:2609. 21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and often requiring large vocabularies.
By Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le, Phu Gia Hoang, Dat Tien Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled.
Multilingual Large Language Models (LLMs) traditionally rely on a single vocabulary shared by all supported languages, which can lead to uneven compression across them. Moreover, their large embedding...
arXiv:2606. 09234v1 Announce Type: cross Abstract: Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently.
By Changfeng Gao, Yong Ren, Jun Yuan, Ye Bai, Zhao You, ShiDong Shang
The paper proposes a modular tokenizer framework for multilingual large language models, allowing the creation of language‑specific subtokenizers that match monolingual compression quality. It introduces a pretraining strategy that samples these subtokenizers to limit predictions to relevant vocabularies, enabling efficient training and inference. This approach reduces memory usage and speeds up inference without compromising performance.
By Franck Signe, Hippolyte Pilchen, Fran\c{c}ois Yvon, \'Edouard Grave
While Large Language Models excel in natural language processing, efficiently extending their capabilities to spoken input remains a significant challenge. Existing methods for building SpeechLLMs oft...
arXiv:2609.09974v1 Announce Type: new
Abstract: Grapheme-to-phoneme conversion (G2P) refers to the task of converting a sequence of graphemes to a corresponding sequence of phonemes. While Filipino G...
By Lorenz Bernard Marqueses, Paulo Grane Gabriel Silva, Chastine Cabatay, Ericson Adler Tan, Ann Franchesca Laguna
arXiv:2606. 16019v1 Announce Type: cross Abstract: Expert phonetic annotation is costly, especially for non-standard dialects and atypical speech.
By Alexander Metzger, Aruna Srivastava, Ruslan Mukhamedvaleev
arXiv:2607. 01238v1 Announce Type: cross Abstract: Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling.
By Priyam Mazumdar, Yurii Halychanskyi, Steven Guo, Mark Hasegawa-Johnson, Volodymyr Kindratenko
arXiv:2609.10296v1 Announce Type: new
Abstract: Non-invasive speech decoding remains constrained by the low signal-to-noise ratio of neural recordings, which makes fine-grained reconstruction of phon...
By Gilad D. Landau, Dulhan Jayalath, Oiwi Parker Jones
arXiv:2609.23191v1 Announce Type: new
Abstract: Speech-text space alignment is a multimodal representation learning method consisting to map different speech and text into a shared representation spa...
By Yannick Yomie Nzeuhang, Marie Tahon, Paulin Melatagia Yonta