no code implementations • 24 Feb 2024 • Xia Liang, Xingjian Du, Jiaju Lin, Pei Zou, Yuan Wan, Bilei Zhu
Large Language Models (LLM) have shown encouraging progress in multimodal understanding and generation tasks.
no code implementations • 4 Dec 2022 • Junchao Lin, Yuan Wan, Jingwen Xu, Xingchen Qi
However, recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph, making it necessary to learn comprehensive and robust graph structures for downstream tasks, rather than relying only on the raw graph structure.
no code implementations • 10 Oct 2021 • Chao Wang, Zhonghao Li, Benlai Tang, Xiang Yin, Yuan Wan, Yibiao Yu, Zejun Ma
Experiments show that, compared with the baseline models, our proposed model can significantly improve the naturalness of converted singing voices and the similarity with the target singer.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 29 Dec 2020 • Yao Wang, Yuan Wan
The finite zero temperature limits of the diffusion constants are then naturally understood as a result of the finite mean free path of the normal modes due to the effective disorder.
Strongly Correlated Electrons Statistical Mechanics
no code implementations • 28 Oct 2020 • Zhonghao Li, Benlai Tang, Xiang Yin, Yuan Wan, Ling Xu, Chen Shen, Zejun Ma
Singing voice conversion (SVC) aims to convert the voice of one singer to that of other singers while keeping the singing content and melody.
3 code implementations • 5 Oct 2020 • Qiuqiang Kong, Bochen Li, Xuchen Song, Yuan Wan, Yuxuan Wang
In addition, previous AMT systems are sensitive to the misaligned onset and offset labels of audio recordings.
Sound Audio and Speech Processing
no code implementations • 23 Apr 2020 • Yu Gu, Xiang Yin, Yonghui Rao, Yuan Wan, Benlai Tang, Yang Zhang, Jitong Chen, Yuxuan Wang, Zejun Ma
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders.
no code implementations • IEEE Xplore 2020 • Yuan Wan, Shengzi Sun, Cheng Zeng
This method reduces the high-dimensional data to the low dimensions and unifies different views to a combined weight matrix.
6 code implementations • 7 Feb 2019 • Jin-Guo Liu, Yi-Hong Zhang, Yuan Wan, Lei Wang
One can obtain a matrix product state (MPS) representation of the ground state using a number of qubits smaller than the physical degrees of freedom.
Quantum Physics Strongly Correlated Electrons