|
|
| Fall 2003: CLSP Seminar Series | Tuesday, May 13, 2008 |
As speech recognition and natural language processing technologies continue to improve, the day of truly conversational interfaces nears. These systems will not simply recognize and understand spoken utterances but will be able to engage in intelligent dialogues through the integration of contextual knowledge from the discourse, information about the current speaker, and common sense reasoning. This talk will first present an overview of the conversational interface technologies developed at MIT. Next, several research projects within the conversational system paradigm will be discussed. These include the computation and integration of recognition confidence scores into the understanding and dialogue components of spoken dialogue systems, the use of speaker identification in personalizable systems, and multi-lingual recognition and understanding. The talk will conclude with an update of on-going work in the area of multi-modal conversational interfaces.
| The Center for Language and Speech Processing The Johns Hopkins University 3400 North Charles Street, Barton Hall Baltimore, MD 21218 | |||||
 | Telephone: (410) 516-4237 | | Fax: (410) 516-5050 | | E-mail: clsp@clsp.jhu.edu |