Search papers, labs, and topics across Lattice.
Andong Li, Xiaodong Li, and Chengshi Zheng are with the Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences, Beijing, 100190, China, and also with University of Chinese Academy of Sciences, Beijing, 100049, China. (Email: liandong@mail.ioa.ac.cn, lxd@mail.ioa.ac.cn, cszheng@mail.ioa.ac.cn) Zhihang Sun is with School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China. Tong Lei, Rilin Chen and Dong Yu are with Tencent AI Lab. Corresponding author: Chengshi Zheng
3
0
6
2
Range-Null Space Decomposition offers a surprisingly effective and scalable approach to neural vocoders, outperforming existing methods while using a lightweight network structure.
Ditch the training data: S2CDR achieves state-of-the-art cross-domain recommendation by smoothing and sharpening user-item interactions with ODEs, all without any training.
Ditch mel-spectrograms: a hierarchical subspace latent diffusion model directly maps lip movements to audio codec latent space, achieving state-of-the-art lip-to-speech synthesis.
