LY Corporation R&D

Our papers have been accepted at ICASSP 2025 (external link).

Aligned Contrastive Learning for Text-to-Music Retrieval
Tatsuya Komatsu, Hokuto Munakata, Takuya Hasumi, Yusuke Fujita

Music tagging with classifier group chains
Takuya Hasumi, Tatsuya Komatsu, Yusuke Fujita

DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information
Shota Nakada, Taichi Nishimura, Hokuto Munakata, Masayoshi Kondo, Tatsuya Komatsu

Language-based Audio Moment Retrieval
Hokuto Munakata, Taichi Nishimura, Shota Nakada, Tatsuya Komatsu

Pre-training with Synthetic Patterns for Audio
Yuchi Ishikawa, Tatsuya Komatsu, Yoshimitsu Aoki (Keio University)

Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control
Ryuichi Yamamoto, Yuma Shirahata, Masaya Kawamura, Kentaro Tachibana

Investigating Factors Related to the Naturalness of Synthesized Unison Singing
Kaito Nishizawa (Nagoya University), Ryuichi Yamamoto, Wen-Chin Huang (Nagoya University), Tomoki Toda (Nagoya University)