no code implementations • 24 May 2024 • Chang Li, Ruoyu Wang, Lijuan Liu, Jun Du, Yixuan Sun, Zilu Guo, Zhenrong Zhang, Yuan Jiang
To overcome these challenges, we introduce a novel quality-aware masked diffusion transformer (QA-MDT) approach that enables generative models to discern the quality of input music waveform during training.
Ranked #1 on Text-to-Music Generation on MusicCaps
no code implementations • 17 Sep 2023 • Zilu Guo, Jun Du, Chin-Hui Lee
The starting state is noisy speech and the ending state is clean speech.
1 code implementation • 14 Jun 2023 • Zilu Guo, Jun Du, Chin-Hui Lee, Yu Gao, Wenbin Zhang
The goal of this study is to implement diffusion models for speech enhancement (SE).
no code implementations • 4 Dec 2021 • Longtian Qiu, Renrui Zhang, Ziyu Guo, Ziyao Zeng, Zilu Guo, Yafeng Li, Guangnan Zhang
Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning.