URI | http://purl.tuc.gr/dl/dias/F19FB843-1CC7-4A05-86A8-839882F90452 | - |
Αναγνωριστικό | https://www.isca-speech.org/archive/Interspeech_2016/abstracts/1273.html | - |
Αναγνωριστικό | https://doi.org/10.21437/Interspeech.2016-1273 | - |
Γλώσσα | en | - |
Μέγεθος | 5 pages | en |
Τίτλος | Root cause analysis of miscommunication hotspots in spoken dialogue systems | en |
Δημιουργός | Georgiladakis Spyridon | en |
Δημιουργός | Γεωργιλαδακης Σπυριδων | el |
Δημιουργός | Athanasopoulou Georgia | en |
Δημιουργός | Αθανασοπουλου Γεωργια | el |
Δημιουργός | Meena Raveesh | en |
Δημιουργός | Lopes José David Aguas | en |
Δημιουργός | Chorianopoulou Arodami | en |
Δημιουργός | Χωριανοπουλου Αροδαμη | el |
Δημιουργός | Palogiannidi Elisavet | en |
Δημιουργός | Παλογιαννιδη Ελισαβετ | el |
Δημιουργός | Iosif Ilias | en |
Δημιουργός | Ιωσηφ Ηλιας | el |
Δημιουργός | Skantze Gabriel | en |
Εκδότης | International Speech and Communication Association | en |
Περίληψη | A major challenge in Spoken Dialogue Systems (SDS) is the detection of problematic communication (hotspots), as well as the classification of these hotspots into different types (root cause analysis). In this work, we focus on two classes of root cause, namely, erroneous speech recognition vs. other (e.g., dialogue strategy). Specifically, we propose an automatic algorithm for detecting hotspots and classifying root causes in two subsequent steps. Regarding hotspot detection, various lexico-semantic features are used for capturing repetition patterns along with affective features. Lexico-semantic and repetition features are also employed for root cause analysis. Both algorithms are evaluated with respect to the Let's Go dataset (bus information system). In terms of classification unweighted average recall, performance of 80% and 70% is achieved for hotspot detection and root cause analysis, respectively. | en |
Τύπος | Πλήρης Δημοσίευση σε Συνέδριο | el |
Τύπος | Conference Full Paper | en |
Άδεια Χρήσης | http://creativecommons.org/licenses/by/4.0/ | en |
Ημερομηνία | 2018-11-19 | - |
Ημερομηνία Δημοσίευσης | 2016 | - |
Θεματική Κατηγορία | Miscommunication detection | en |
Θεματική Κατηγορία | Miscommunication root causes | en |
Θεματική Κατηγορία | Spoken dialogue systems | en |
Βιβλιογραφική Αναφορά | S. Georgiladakis, G. Athanasopoulou, R. Meena, J. Lopes, A. Chorianopoulou, E. Palogiannidi, E. Iosif, G. Skantze and A. Potamianos, "Root cause analysis of miscommunication hotspots in spoken dialogue systems," in 17th Annual Conference of the International Speech Communication Association, 2016, pp. 1156-1160.
doi: 10.21437/Interspeech.2016-1273 | en |