About us-eng

The Center for Speech and Language Technology (CSLT), Tsinghua University, was established with the goal of conducting edge-cutting research on intelligent human-machine interactions, particularly the research on speech and language techniques. The main topics involve speech recognition, biometric certification, spoken information discovery, natural language processing and understanding.

The predecessor of CSLT, the center for speech technology (CST) was established in 1979. In Feb. 2007, CST was merged with a few other research groups including the speech technology group and speech chip group of the department of electronic & electricity, the future information technology (FIT) center of RIIT and the AI research department of Tsinghua National Lab of Information Science & Technology (TNList). The new institute is dedicated to fundamental research on speech and language technologies, as well as practical delivers for the the industry.

CSLT consists of three labs: the speech recognition (ASR) lab, the voice print recognition (VPR) lab, the natural language processing (NLP) lab. A large number of famous researchers are in the advisory board, including Prof. Victor Zue (MIT), B.-H. (Fred) Juang, William Byrne (Cambridge), Dan Jurafsky (Standford), Richard Stern (CMU), Litang Fang(Tsinghua), Wenhu Wu(Tsinghua), Runsheng Liu(Tsinghua).