Speech and Language Technology R&D Center
Mission: The mission of the Speech and Language Technologies R&D Center (abbreviated as Center for Speech and Technologies, CSLT) is to develop advanced speech and language processing technologies to meet the growing demand for information processing in mobile Internet era between individuals anywhere at anytime with any media through advanced human-machine interaction methods. CSLT will make full use of the superiorities in the integrated and interdisciplinary advantages in the School of Information Science and Technology as well as worldwide collaboration environments, focus on the industrialization of the speech and language technologies, develop innovative solutions in the areas of multi-language and multi-platform speech recognition, pattern recognition of multi-modal biometric features and natural language processing, enable a series of service and products with intellectual property of the center. CSLT will commit itself to build a team of talents, who hold advanced technologies, have creative spirits and engineering experiences, and are able to participate in the international competition. CSLT will make the great contribution in pushing Tsinghua University to enter into the first class university of the world in speech and language processing field through technological innovation.
History: CSLT was founded in February 2007. CSLT is led by faculty members from research groups of the School of Information Science and Technology, including the Center for Speech Technology (CST) of the State Key Laboratory of Intelligent Technology and Systems, the Speech Processing Technology Group and the Speech-on-Chip Group of the Department of Electronic Engineering, the Future Information Technology (FIT) R&D Center of Research Institute of Information Technology, as well as the Division of Computer Science and Artificial Intelligence of Tsinghua National Laboratory for Information Science and Technology.
In 2003, FIT funded ITS (Intelligent Transportation Systems), home networking, and digital multimedia. Among them, Tsinghua University ITS Research Center was established based on the ITS projects, and the home networking project grew into Tsinghua-Guoguang Digital Media Research Institute.
Guideline: Keeping the guideline as “base on the applications, advocate the innovations, focus on the emphases and spur with long accumulation” in the mind, CSLT faces the challenges in the areas of speech and language processing technologies. Main research directions of the center include speech recognition, speaker recognition and language understanding. CSLT optimizes its resources allocation and effectively distributes human resources. Through exploring and setting up effective pattern of “cooperative of Industry, Education and Research”, CSLT is to strengthen core competency in intellectual property through technology innovation and industrialization, and is to promote the development of applied fundamental research and technology innovation.
Organization: CSLT has six research groups: Speech Recognition Group, Speaker Recognition Group, Speech-on-Chip Group, Intelligent Searching Group, Language Understanding Group and Resource and Standardization Group. In order to speed up the development and improve the research level, CSLT established an advisory committee that composed of famous experts in the world. They are: Victor Zue (MIT, IEEE Fellow, NAE member), B.-H. (Fred) Juang (GeorgiaTech, IEEE Fellow, NAE member)，William Byrne (Cambridge), Dan Jurafsky (Stanford), Richard Stern (CMU)，Fang Ditang (Tsinghua), Wu Wenhu (Tsinghua), and Liu Runsheng (Tsinghua).