As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This paper proposes a new technique to enhance the performance of the input interface of spoken dialogue systems, which relies on the correction of speech recognition errors at two levels: statistical and linguistic. experiments carried out with a spoken dialogue system designed for the fast food domain show that the technique allows enhancing word accuracy, speech understandint and task completion rules.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.