TY  - BOOK
AU  - Schmitt,Alexander
AU  - Minker,Wolfgang
ED  - SpringerLink (Online service)
TI  - Towards Adaptive Spoken Dialog Systems
SN  - 9781461445937
AV  - TK5102.9 
U1  - 621.382 23
PY  - 2013///
CY  - New York, NY
PB  - Springer New York, Imprint: Springer
KW  - Engineering
KW  - Data mining
KW  - User interfaces (Computer systems)
KW  - Computer graphics
KW  - Signal, Image and Speech Processing
KW  - Data Mining and Knowledge Discovery
KW  - User Interfaces and Human Computer Interaction
KW  - Computer Imaging, Vision, Pattern Recognition and Graphics
N1  - Introduction -- Background and Related Research -- Interaction Modeling and Platform Development -- Novel Strategies for Emotion Recognition -- Novel Approaches to Pattern-based Interaction Quality Modeling -- Statistically Modeling and Predicting Task Success -- Conclusion and Future Directions
N2  - In Monitoring Adaptive Spoken Dialog Systems, authors Alexander Schmitt and Wolfgang Minker investigate statistical approaches that allow for recognition of negative dialog patterns in Spoken Dialog Systems (SDS). The presented stochastic methods allow a flexible, portable and  accurate use.  Beginning with the foundations of machine learning and pattern recognition, this monograph examines how frequently users show negative emotions in spoken dialog systems and develop novel approaches to speech-based emotion recognition using hybrid approach to model emotions. The authors make use of statistical methods based on acoustic, linguistic and contextual features to examine the relationship between the interaction flow and the occurrence of emotions using non-acted  recordings several thousand real users from commercial and non-commercial SDS. Additionally, the authors present novel statistical methods that spot problems within a dialog based on interaction patterns. The approaches enable future SDS to offer more natural and robust interactions. This work provides insights, lessons and  inspiration for future research and development, not only for spoken dialog systems, but for data-driven approaches to human-machine interaction in general
UR  - http://dx.doi.org/10.1007/978-1-4614-4593-7
ER  -