2件 （「Lingua Cultura」）

Wav2Gloss: Generating Interlinear Glossed Text from Speech プレプリント PDF

He, Taiqi・Choi, Kwanghee・Tjuatja, Lindia・Robinson, Nathaniel R.・Shi, Jiatong・Watanabe, Shinji・Neubig, Graham・Mortensen, David R.・Levin, Lori ·2024-06-06 ·『arXiv』

doi:10.48550/arXiv.2403.13169

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis プレプリント

Lianbo Liu・Shiao Zhu・Kai Washizaki・Reo Yoneyama・Haesung Jeon・Mengjie Zhao・Yusuke Fujita・H. Z. Shi・Nao Yoshida・Gao Y・Roman Koshkin・Yukiya Hono・Yui Sudo ·2026-06-24 ·Cornell University

arxiv.org