Education
- B.E. in Computer Science and Technologies, Tsinghua University, 2015 to 2019
- B.S. in Pure and Applied Mathematics (Second Major), Tsinghua University, 2016 to 2019
- Ph.D. in Computer Science, University of Southern California, 2019 to 2024 (expected)
Publications
- Suping Zhou, Jia Jia, Yufeng Yin, Xiang Li, Yang Yao, Ying Zhang, Zeyang Ye, Kehua Lei, Yan Huang, Jialie Shen. Understanding the Teaching Styles by an Attention based Multi-task Cross-media Dimensional Modeling. In the Proceedings of the 27th ACM International Conference on Multimedia (ACM MM’19) [pdf]
- Jia Jia, Suping Zhou, Yufeng Yin and Boya Wu. Inferring Emotions from Large-scale Internet Voice Data. IEEE Transactions on Multimedia 2019 (TMM’19) [pdf]
- Suping Zhou, Jia Jia, Qi Wang, Yufei Dong, Yufeng Yin and Kehua Lei. Inferring Emotion from Conversational Voice Data: A Semi-supervised Multi-path Generative Neural Network Approach. In the Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI’18) [pdf]
Awards & Honors
- Tsinghua University Department of Computer Science and Technologies Outstanding Graduates, 2019
- Tsinghua University Academic Excellence Scholarship (Top 10% of Department), 2017
- Tsinghua University Comprehensive Excellence Scholarship (Top 5% of Department) , 2016
Research Experience
Tsinghua University Human-Computer Speech Interaction Research Group, 2016 to 2019
Advisor: Prof. Jia Jia
- Understanding the Teaching Styles by an Attention based Multi-task Cross-media Dimensional Modeling, 2018 to 2019
- Established a fully-annotated voice data set (4,451 utterances) with pleasure and arousal values
- Created a two-dimensional Teaching Style Semantic Space (TSSS) to determine teachers’ teaching styles
- Proposed a multi-task cross-media model to map acoustic features to coordinates on the TSSS
- Co-authered a paper published in ACM MM’19
- Inferring Emotions from Large-scale Internet Voice Data, 2017 to 2018
- Employed DNN and LSTM with autoencoders to infer emotions from large-scale internet voice data
- Processed data, created neural networks, conducted experiments and edited the paper
- Co-authored a paper published in TMM’19
- Inferring Emotion from Conversational Voice Data: A Semi-supervised Multi-path Generative Neural Network Approach, 2017
- Proposed a novel model to infer emotion from conversational voice data
- Collected over 24,000 real-world utterance, processed data and edited paper
- Co-authored a paper published in AAAI’18
Stanford University Human-Computer Interaction Research Group, 2018
Advisors: Prof. James Landay, Prof. Emma Brunskill
The Smart Primer, 2018
- A personal tutor for children that uses narrative and embedded physical world activities to enhance learning
- Stanford University Undergraduate Visiting Research Program (UGVR)
- Created a chat bot and a quiz bot to guide users
- Worked as the architect of the whole project for both frontend and backend coding
Work Experience
- Fall 2018: Teaching Assistant for Principles of Signal Processing
- Tsinghua University
- Helped Prof. Jia Jia to prepare lessons, especially those including mathematical derivations
- Participated in editing slides, answering students’ questions and correcting homework
- Summer 2018: Research Assistant
- Stanford University Human-Computer Interaction Research Group
- Developed an educational software on tablets named the Smart Primer
- Supervisor: Prof. James Landay, Prof. Emma Brunskill
Skills & Others
- Language: Mandarin, English
- Programming Languages: C, C++, Python, Java, JavaScript, R, HTML, Assembly, LaTeX, Matlab, Qt
- Research Skills: vim, git, bash, cmake, gcc, gdb
- Software: Visual Studio, Android Studio, Eclipse