Shun Lei
Shenzhen International Graduate School, Tsinghua University
- leis21@mails.tsinghua.edu.cn
- Google Scholar
- Github
- Shenzhen, Guangdong, China
I'm currently a PhD student at Shenzhen International Graduate School, Tsinghua University
(SIGS, THU) in Shenzhen. My supervisor is Prof. Zhiyong Wu. Before that,
I received my bachelor’s degree from Sichuan University.
My current research interests include Expressive Speech Synthesis, Music Generation, 3D Dance Generation, Singing Voice Synthesis, etc.
News
- [Apr 2024] Two paper is accepted to ICASSP 2024.
- [Dec 2023] One paper is accepted to AAAI 2024.
- [Oct 2023] One paper is accepted to IEEE/ACM Transactions on Audio, Speech and Language Processing
- [Jul 2023] One paper is accepted to Interspeech 2023 as an Oral presentation.
- [Jun 2023] One paper is recognized as one of the top 3% of all papers accepted at ICASSP 2023.
- [May 2023] Two paper are accepted to ICASSP 2023 with one Oral presentation.
- [Oct 2022] One paper is accepted to COLING 2023 as an Oral presentation.
- [Sep 2022] Two paper are accepted to Interspeech 2022.
- [May 2022] One paper is accepted to ICASSP 2022.
- [Jul 2021] One paper is accepted to IJCNN 2021.
Publications [Google Scholar]
2024:
-
Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic PromptsShun Lei, Yixuan Zhou, Liyang Chen, Dan Luo, Zhiyong Wu, Xixin Wu, Shiyin Kang, Tao Jiang, Yahui Zhou, Yuxing Han, Helen MengICASSP, 2024 [Paper]
-
SimCalib: Graph Neural Network Calibration based on Similarity between NodesBoshi Tang, Zhiyong Wu, Xixin Wu, Qiaochu Huang, Jun Chen, Shun Lei, Helen MengAAAI, 2023 [Paper]
-
MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech SynthesisShun Lei, Yixuan Zhou, Liyang Chen, Zhiyong Wu, Xixin Wu, Shiyin Kang, Helen MengIEEE/ACM Transactions on Audio, Speech and Language Processing [Paper]
-
Towards Spontaneous Style Modeling with Semi-supervised Pre-training for Conversational Text-to-Speech SynthesisWeiqin Li, Shun Lei, Qiaochu Huang, Yixuan Zhou, Zhiyong Wu, Shiyin Kang, Helen MengInterspeech, 2023 (Oral) [Paper]
-
Context-Aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook Speech SynthesisShun Lei, Yixuan Zhou, Liyang Chen, Zhiyong Wu, Shiyin Kang, Helen MengICASSP, 2023 (Oral, Top 3% Paper) [Paper]
-
GTN-Bailando: Genre Consistent long-Term 3D Dance Generation Based on Pre-Trained Genre Token NetworkHaolin Zhuang, Shun Lei, Long Xiao, Weiqin Li, Liyang Chen, Sicheng Yang, Zhiyong Wu, Shiyin Kang, Helen MengICASSP, 2023 [Paper]
-
Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech SynthesisXueyuan Chen, Shun Lei, Zhiyong Wu, Dong Xu, Weifeng Zhao, Helen MengCOLING, 2023 (Oral) [Paper]
-
Towards Multi-Scale Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech SynthesisShun Lei, Yixuan Zhou, Liyang Chen, Hu Jiankun, Zhiyong Wu, Shiyin Kang, Helen MengInterspeech, 2022 [Paper]
-
Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic InformationShaohuan Zhou, Shun Lei, Weiya You, Deyi Tuo, Yuren You, Zhiyong Wu, Shiyin Kang, Helen MengInterspeech, 2022 [Paper]
-
Towards Expressive Speaking Style Modelling with Hierarchical Context Information for Mandarin Speech SynthesisShun Lei, Yixuan Zhou, Liyang Chen, Zhiyong Wu, Shiyin Kang, Helen MengICASSP, 2022 [Paper]
-
MRC-LSTM: A Hybrid Approach of Multi-scale Residual CNN and LSTM to Predict Bitcoin PriceQiutong Guo, Shun Lei, Qing Ye, Zhiyang FangIJCNN, 2021 [Paper]