direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments


Predicting the Quality and Usability of Spoken Dialogue Services
Zitatschlüssel moeller2008j
Autor Möller, Sebastian and Engelbrecht, Klaus-Peter and Schleicher, Robert
Seiten 730–744
Jahr 2008
ISSN 0167-6393
DOI 10.1016/j.specom.2008.03.001
Adresse Amsterdam, Netherlands
Journal Speech Communication
Jahrgang 50
Nummer 8-9
Verlag Elsevier Science Publishers B. V
Zusammenfassung In this paper, we compare different approaches for predicting the quality and usability of spoken dialogue systems. The respective models provide estimations of user judgments on perceived quality, based on parameters which can be extracted from interaction logs. Different types of input parameters and different modeling algorithms have been compared using three spoken dialogue databases obtained with two different systems. The results show that both linear regression models and classification trees are able to cover around 50\% of the variance in the training data, and neural networks even more. When applied to independent test data, in particular to data obtained with different systems and/or user groups, the prediction accuracy decreases significantly. The underlying reasons for the limited predictive power are discussed. It is shown that - although an accurate prediction of individual ratings is not yet possible with such models - they may still be used for taking decisions on component optimization, and are thus helpful tools for the system developer
Link zur Publikation Download Bibtex Eintrag

Zusatzinformationen / Extras


Schnellnavigation zur Seite über Nummerneingabe