Employing Filler Model Based Word Level Confidence Measures
(0 Bewertungen)15
490 Lesepunkte
Buch (kartoniert)
Buch (kartoniert)
48,99 €inkl. Mwst.
Zustellung: Mi, 09.07. - Fr, 11.07.
Versand in 4 Tagen
Versandkostenfrei
Bestellen & in Filiale abholen:
Empfehlen
In conversational dialogue applications it is critical to understand the requests accurately. However, the performance of current speech recognition systems are far from perfect. In order to function effectively with imperfect speech recognition, an accurate confidence scoring mechanism should be employed. To determine a confidence score for a hypothesis, certain confidence features are combined. In this work, the performance of filler-model based confidence features are investigated. Five types of filler model are defined: triphone-network, phone-network, phone-class network, 5-state catch-all model and 3-state catch-all model. First all models are evaluated in terms of their ability to correctly tag (miss or hit) recognition hypotheses. Then the performance of reliable combinations of these models are evaluated to show how certain reliable combinations of filler models could significantly improve the accuracy of the confidence annotation. Moreover to show the practical side of the work, an implementation of a real dialogue management system is described.
University(ITU), TR and MS degree from Sabanc University, TR both
at computer science. After his graduation he spent 4 years in
industry as an R&D Engineer for Verifone and Accenture. Currently
he is pursuing the PhD degree at ITU. His research interests
include inverse problems in Computer Vision.
Bewertungen
0 Bewertungen
Es wurden noch keine Bewertungen abgegeben. Schreiben Sie die erste Bewertung zu "Increasing Robustness of Spoken Dialogue Systems" und helfen Sie damit anderen bei der Kaufentscheidung.