When building a new spoken dialogue application, large amounts of domain specific data are required. This paper addresses the issue of generating in-domain training data when litt...
Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to ...
This paper describes the application of the PARADISE evaluation framework to the corpus of 662 human-computer dialogues collected in the June 2000 Darpa Communicator data collecti...
Marilyn A. Walker, Rebecca J. Passonneau, Julie E....
While most dialogue systems restrict themselves to the adjustment of the propositional contents, our work concentrates on the generation of stylistic variations in order to improve...
The NWO Priority Programme Language and Speech Technology is a 5-year research programme aiming at the development of spoken language information systems. In the Programme, two al...
Gert Veldhuijzen van Zanten, Gosse Bouma, Khalil S...