LINEヤフーの研究開発

以下の論文がICASSP 2026（外部サイト）で採択されました

CASTELLA: LONG AUDIO DATASET WITH CAPTIONS AND TEMPORAL BOUNDARIES
Hokuto Munakata, Takehiro Imamura (Nagoya University), Taichi Nishimura, and Tatsuya Komatsu

Wave-Trainer-Fit: Neural Vocoder with Trainable Prior and Fixed-Point Iteration towards High-Quality Speech Generation from SSL features
Hien Ohnaka (Nara Institute of Science and Technology), Yuma Shirahata, Masaya Kawamura

ONLINE REGISTER FOR DUAL-MODE SELF-SUPERVISED SPEECH MODELS: MITIGATING THE LACK OF FUTURE CONTEXT
Keita Goto, Takashi Maekaku, Jin Sakuma, Jinchuan Tian (Carnegie Mellon University), Yusuke Shinohara, Shinji Watanabe (Carnegie Mellon University)

AUDIO-VISUAL FEATURE FUSION FOR CALIBRATING RELEVANCE SCORES OF VIDEO MOMENT RETRIEVAL
Takehiro Imamura (Nagoya University), Tatsuya Komatsu, Hokuto Munakata, Tomoki Toda (Nagoya University)

CC-G2PnP: Streaming Grapheme-to-Phoneme and prosody with Conformer-CTC for unsegmented languages
Yuma Shirahata Ryuichi Yamamoto

3-KEY-INPUT: EXPLORING THE THEORETICAL MINIMUM KEYS FOR TEXT ENTRY
Naoki Kimura