Biography
Kai Yu entered the Department of Automation at Tsinghua University, P.R.China in 1994. After obtaining B.Eng. in 1999, he continued his study for M.Sc. in the State Key Laboratory of Pattern Recognition and Intelligence Systems in the same department untill 2002. He then joined the Machine Intelligence Laboratory (MIL) (formerly the Speech Vision and Robotics (SVR) group), where he obtained his PhD in 2006 under the supervision of Prof. Mark Gales. He worked as a research associate, and later senior research associate in MIL until 2012 with Prof. Phil. Woodland and Prof. Steve Young. He is now a research professor at Computer Science and Engineering Department, Shanghai Jiao Tong University.
He is a senior member of IEEE, a member of ISCA. He serves as a member of the IEEE Speech and Language Processing Technical Committee. He is also a member of the technical committee of Language, Auditory and Music Branch of the acoustic society of China, and a member of the technical committee of the Speech Technology Industry Union. He was selected into the Programme for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.
Research interests
- Spoken dialogue system, speech understanding and human computer interaction
- Adaptation and adaptive training in speech recognition and synthesis
- Discriminative training of acoustic models
- HMM based statistical speech synthesis
- Bayesian inference and graphical model in pattern recognition
- Statistical learning theory and kernel methods
- Signal processing, image processing and understanding
- Application of machine intelligence
Projects
Current Projects
- Programme for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning
- Human-computer speech interaction (NSFC Excellent Young Researcher Project)
- High performance and robust speech and speaker recognition system (Industry)
- Speaker recognition and speech synthesis for mobile systems (Industry)
Past Projects
- Automatic Communication Skill Evaluation. (Cambridge Assessment)
- Probabilistic Adaptive Real-time Learning And Natural Conversational Engine (PARLANCE) (EU FP7)
- Robust dialogue for infotainment.
- Computational Learning in Adaptive Systems for Spoken Conversation (CLASSIC) (EU FP7)
- Global Autonomous Language Exploitation (GALE) (DARPA funded project)
- Effective, Affordable Reusable Speech-to-text (EARS) (DARPA funded project)
Activities
Membership
- IEEE Senior Member
- ISCA Member
- Member of the technical committee of Language, Auditory and Music Branch of the acoustic society of China
- Member of the technical committee of the Speech Technology Industry Union
Service
- InterSpeech 2014 - Area chair (dialogue systems)
- EUSIPCO 2014 - Area chair (speech processing)
- IEEE ChinaSIP 2013 - Summer school chair
- IEEE ASRU 2011 - Publication chair
- EUSIPCO 2011 - Area chair (speech processing)
- IUI 2010 - Programme committee member
- InterSpeech 2009 - Area chair (speech recognition)
- Regular reviewer for internatiaonal conferences and journals
Conferences: ICASSP, INTERSPEECH, ASRU, EACL, IUI, CHI, EUSIPCO
Journals: IEEE Trans. on ASL, IEEE Signal Processing Letters, Speech Communication, Computer Speech & Language, IET Signal Processing Letters, Multimedia Tools and Application, Science China - Research grant reviewer
National Natural Science Foundation of China (NSFC)
Foundation for Polish Science (FNP)
Contact
Kai Yu
SpeechLab
Computer Science and Engineering Department Tel: +86 21 34207864
3-539 SEIEE Building, 800 Dongchuan Road, Minhang District, Shanghai
Email: kai.yu@sjtu.edu.cn
200240, China