Talk videos can be found here at bilibili; Code here at github; Chinese blogs here at zhihu; Chinese news here at weibo; English news here at X.
Recent News
Nov. 2026: We will organize the 3rd Seminar on Multilingual Speech and Language AI Technologies (3rd SALT-Multilingual; 第三届多语言智能语音与语言技术研讨会) as a special session at NCMMSC 2026 in Hengqin, China. You are warmly invited to join us!
Oct. 2026: We will organize a Thematic Forum "Are Large Models the Watt Steam Engine? A Critical Analysis of Efficiency, Reliability, and Scaled Application" at CNCC (China National Computer Congress) 2026, Chengdu, China. You are warmly invited to join us!
URL (in Chinese)
Apr. 2, 2026:
Our tutorial, “Advances in Data-Efficient Multilingual and Crosslingual Speech Recognition Powered by LLMs,” by Saierdaer Yusuyin, Hexin Liu, Eng Siong Chng, and Zhijian Ou, has been accepted for INTERSPEECH 2026. It is scheduled for the morning of Sunday, 27 September 2026, at the International Convention Centre Sydney. We warmly welcome colleagues and friends interested in these exciting topics to stay tuned and join us for the tutorial.
Tutorial Website
GENERAL INFORMATION
Curriculum Vitae| 2024.12 - present | Professor. |
| 2018.12 - present | Co-founder and Chief Scientist of TasiTech. |
| 2008.12 - 2024.12 | Associate professor. |
| 2014.08 - 2015.07 | Visiting Scholar, Beckman Institute, University of Illinois at Urbana-Champaign. |
| 2003.08 - 2008.12 | Assistant professor, Department of Electronic Engineering, Tsinghua University, Beijing, China. |
| 1998.09 - 2003.07 | Ph.D. in electronic engineering from Tsinghua University, Beijing, China. |
| 1994.09 - 1998.07 | B.S. with the highest honor in electronic engineering from Shanghai Jiaotong University, Shanghai, China. |
RESEARCH INTERESTS
- Speech and Language Processing (particularly speech recognition and dialogue systems)
- Machine Intelligence (particularly with graphical models and deep learning)
I'm broadly interested in Dealing with Uncertainty for Intelligent Systems. The two fundamental problems are first to construct probabilistic models of the studied phenomenon using human knowledge and machine learning algorithms, and second to find efficient ways of implementing probabilistic inference with those models. Graphical models have emerged as a general framework for describing and applying probabilistic models, while the core is probability theory and mathematical statistics.
Current interests are Speech and Language Processing, by proposing new models of speech and language, developing new methods for learning and inference with those models, and applying them to real tasks in speech and language processing. 100,000 years ago, humans started to speak so they could free up their hands. Is it going to happen again? Getting rid of keyboards and talking to machines is not a dream in the near future, I believe. Moreover, efficient searching, mining, and browsering the large amounts of digital media, in which speech is often an indispensable component, also needs speech signal and information processing techniques.
RESEARCH PROJECTS
TEACHING
- Theory and Applications of Probabilistic Graphical Models, since 2004 Fall.
- Probability and Stochastic Processes (1), since 2012 Spring.
- Probability and Stochastic Processes (2), since 2012 Fall.
- Mathematics and engineering applications, 2005 Spring - 2011 Spring.
PROFESSIONAL ACTIVITIES
- IEEE Senior Member (2014-present)
- Senior Area Editor (01/2025-01/2028), Associate Editor (05/2019-05/2024), IEEE/ACM Transactions on Audio, Speech and Language Processing (T-ASLP)
- Editorial Board Member (11/2021-07/2025), Computer Speech and Language
- Senior Area Editor (03/2024-03/2029), IEEE Signal Processing Letters
- Chair of Workshops Sub-Committee (2022-2025) and Committee Member (2020-2022, 2023-2025), IEEE Speech and Language Processing Technical Committee (SLTC)
- Committee Member (2019-present), APSIPA Machine Learning and Data Analytics (MLDA) Technical Committee
- Distinguished Member (2022-present), China Computer Federation (CCF)
- Standing Committee Member (2018-present), CCF Speech Conversation and Auditory Technical Committee
- Committee Member (2021-present), Speech Acoustics and Hearing Branch, The Acoustical Society of China (ASC)
- Steering Committee Member (2017-present), National Conference on Man-Machine Speech Communication (NCMMSC)
- Proposal reviewer (2020-present), National Science Foundation of China (NSFC)
- Conference Organizing Committee Member:
INTERSPEECH 2020 Tutorial Chair; SLT 2021 General Chair; ASRU 2021 SPS Liaison; SLT 2022 SPS Liaison; EMNLP 2022 SereTOD Workshop General Chair; SLT 2024 Advisory board; SLT 2024 FutureDial-RAG Challenge General Chair; ISCSLP 2024 Technical Program Chair; NCMMSC Youth Forum Chair (2024, 2025, 2026). - Conference Senior Program Committee member/Area Chair/Meta reviewer:
ICASSP; SLT; ASRU; IJCAI; EMNLP. - Conference Session Chair:
ICASSP; INTERSPEECH; SLT; ASRU; ISCSLP. - Conference Technical Program Committee Member/Scientific Committee Member/Reviewer:
NeurIPS; ICLR; ICML; AAAI; IJCAI; ACL; EMNLP; ACL Rolling Review; ICASSP; INTERSPEECH; MLSP; IWAENC; ISCSLP; NAACL-HLT; CHiME; HSCMA; DSLW. - Journal Reviewer:
T-ASLP; T-SMC; JMLR; SPL; JASA; Science China; Chinese Journal of Electronics; Acta Automatic Sinica; Journal of Computer Science and Technology; Journal of Chinese Information Processing. - Tutorial Speaker:
ISCSLP 2016, 2018; ACPR 2021; ICASSP 2022; INTERSPEECH 2026.
HONORS
- Chinese Institute of Electronics (CIE) Science and Technology Innovation Award, 2025.
- Second Prize, China Broadcast and Internet Media AI Innovation Challenge, 2025.
- Zheng-Junli Teaching and Education Outstanding Award, Electronic Engineering Department, Tsinghua University, 2023.
- Zhang-Yujin Book Award for the monograph “Energy-Based Models with Applications to Speech and Language Processing”, Electronic Engineering Department, Tsinghua University, 2023.
- China Guangxi Provincial Science and Technology Award, 2022.
- First Prize, China Broadcast and Internet Media AI Innovation Challenge, 2021.
- Best Paper Finalist, IEEE Spoken Language Technology Workshop (SLT) 2021, "Efficient Neural Architecture Search For End-To-End Speech Recognition Via Straight-Through Gradients" (Huahuan Zheng, Keyu An, Zhijian Ou).
- Advisor for Beijing Outstanding Undergraduate Thesis "Mixed-feature Random Field Language Models with Applications to Speech Recognition" (Silin Gao), 2020.
- Advisor for Best Student Paper, ISCSLP (International Symposium on Chinese Spoken Language Processing), "Angular Softmax Loss for End-to-end Speaker Verification" (Yutian Li, Feng Gao, Zhijian Ou, and Jiasong Sun), 2018.
- Advisor for Tsinghua University Outstanding Ph.D. Thesis "Statistical Language Models Based on Trans-dimensional Random Fields" (Bin Wang), 2018.
- China NRTA Science and Technology Innovation Award, 2012.
- First-class Award, Tsinghua University Young Teachers Teaching Contest, 2012.
- Award for Mentoring Tsinghua University Outstanding Undergraduate Class, 2010.
- Awards for Mentoring Tsinghua University Outstanding Undergraduate Thesis, 2009, 2011, 2014, 2019, 2020, 2021, 2022.
- Awards for Mentoring Tsinghua University Outstanding Student Research Training (SRT) Project, 2005, 2012.
- Best Paper, NCMMSC (National Conference on Man Machine Speech Communication), "Application of maximum likelihood linear regression to linear prediction HMMs" (Jinyin Wang, Zuoying Wang, and Zhijian Ou), 2005.
- Achieved the best result for Chinese syllable recognition in the 863 Program evaluation in 2003.
- Best Paper, Ph.D. Student Academic Forum, Department of EE, Tsinghua University, 2002.