We show how the DOP model can be used for fast and robust processing of spoken input in a practical spoken dialogue system called OVIS. OVIS, Openbaar Vervoer Informatie Systeem (...
This paper presents a practical method for a global structure analyzing Mgorithm of Japanese long sentences with lexical information, a method which we call Lexical Discourse Gram...
We propose a learning algorithm for a variable memory length Markov process. Human communication, whether given as text, handwriting, or speech, has multi characteristic time scal...
We describe our preliminary work in modeling conversation specifications and policies as positive/negative permissions and obligations. Our model is generic as it is independent o...
The human voice is primarily a carrier of speech, but it also contains non-linguistic features unique to a speaker and indicative of various speaker demographics, e.g. gender, nat...