- Hauptmenü-

Katalogdatenanzeige

Towards Adaptive Spoken Dialog Systems

Kataloginformation Katalogdatensatz500177184 .

Kataloginformation
Feldname	Details
Vorliegende Sprache	eng
ISBN	978-1-4614-4592-0
Name	Schmitt, Alexander
Name	Minker, Wolfgang
Name ANZEIGE DER KETTE	Minker, Wolfgang
T I T E L	Towards Adaptive Spoken Dialog Systems
Verlagsort	New York, NY
Verlag	Springer
Erscheinungsjahr	2013
Erscheinungsjahr	2013
Umfang	Online-Ressource (XIV, 251 p. 67 illus., 15 illus. in color, digital)
Reihe	SpringerLink. Bücher
Notiz / Fußnoten	Description based upon print version of record
Weiterer Inhalt	Towards AdaptiveSpoken DialogSystems; Preface; Acknowledgments; Contents; Acronyms; 1 Introduction; 1.1 Spoken Dialog Systems; 1.1.1 Automatic Speech Recognition; 1.1.2 Semantic Analysis; 1.1.3 Dialog Management; 1.1.4 Language Generation and Text-to-Speech Synthesis; 1.2 Towards Adaptive Spoken Dialog Systems; 2 Background and Related Research; 2.1 Machine Learning: Algorithms and Performance Metrics; 2.1.1 Supervised Learning; 2.1.2 Performance Metrics; 2.2 Emotion Recognition; 2.2.1 Theories of Emotion and Categorization; 2.2.2 Emotional Speech; 2.2.3 Emotional Labeling. 2.2.4 Paralinguistic and Linguistic Features for Emotion Recognition2.2.5 Related Work in Speech-Based Emotion Recognition; 2.3 Approaches for Estimating System Quality, User Satisfaction and Task Success; 2.3.1 Offline Estimation of Quality on Dialog- and System-Level; 2.3.2 Online Estimation of Task Success and User Satisfaction; 2.4 Summary and Discussion; 3 Interaction Modeling and Platform Development; 3.1 Raw Data; 3.2 Parameterization and Annotation; 3.2.1 Interaction Parameters; 3.2.2 Emotion Annotation. 3.3 A Workbench for Supporting the Development of Statistical Models for Online Monitoring3.3.1 Requirements Toward a Software Tool; 3.3.2 The Workbench; 3.3.3 Data Management; 3.3.4 Evaluating Statistical Prediction Models for Online Monitoring; 3.4 Summary and Discussion; 4 Novel Strategies for Emotion Recognition; 4.1 Speech-Based Emotion Recognition; 4.1.1 Paralinguistic Emotion Recognition; 4.1.2 Linguistic Emotion Recognition; 4.2 Dialog-Based Emotion Recognition; 4.2.1 Interaction and Context-Related Emotion Recognition; 4.2.2 Emotional History. 4.2.3 Emotion Recognition in Deployment Scenarios4.3 Evaluation; 4.3.1 Corpora; 4.3.2 Human Performance; 4.3.3 Speech-Based Emotion Recognition; 4.3.4 Dialog-Based Emotion Recognition; 4.3.5 Fusion Strategy; 4.3.6 Emotion Recognition in Deployment Scenarios; 4.4 Summary and Discussion; 5 Novel Approaches to Pattern-Based Interaction Quality Modeling; 5.1 Interaction Quality Versus User Satisfaction; 5.2 Expert Annotation of Interaction Quality; 5.2.1 Annotation Example; 5.2.2 Rating Statistics and Determination of the Final IQ Score; 5.3 A User Satisfaction Study Under Laboratory Conditions. 5.3.1 Lab Study Setup5.3.2 Participants; 5.3.3 Comparison of User Satisfaction and Interaction Quality; 5.4 Input Variables; 5.5 Modeling Interaction Quality and User Satisfaction; 5.6 Evaluation; 5.6.1 Performance Metrics; 5.6.2 Feature Set Composition; 5.6.3 Feature Selection; 5.6.4 Assessing the Model Performance; 5.6.5 Impact of Optimization Through Feature Selection; 5.6.6 Cross-Target Prediction and Portability; 5.6.7 Causalities and Correlations Between Interaction Parameters and IQ/US.; 5.7 Summary and Discussion; 6 Statistically Modeling and Predicting Task Success. 6.1 Linear Modeling
Titelhinweis	Buchausg. u.d.T.ISBN: 978-1-461-44592-0
ISBN	ISBN 978-1-4614-4593-7
	ISBN 1-283-62435-4 ebk
	ISBN 978-1-283-62435-0 MyiLibrary
Klassifikation	TTBM
	UYS
	TEC008000
	COM073000
	*68-02
	68T10
	68T05
	94A05
	005.437
	006.454
	621.382
	TK5102.9
	TA1637-1638
	TK7882.S65
Kurzbeschreibung	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.
SWB-Titel-Idn	373498136
Signatur	Springer E-Book
Bemerkungen	Elektronischer Volltext - Campuslizenz
Elektronische Adresse	$uhttp://dx.doi.org/10.1007/978-1-4614-4593-7
Internetseite / Link	Volltext
Siehe auch	Volltext
Siehe auch	Cover
Siehe auch	Inhaltstext

ISBD-Anzeige Katalogdatensatz500177184

Kategorien-Anzeige Katalogdatensatz500177184

Titel zur Titelsammlung hinzufügen Katalogdatensatz500177184

Kataloginformation500177184 Datensatzanfang . Kataloginformation500177184 Seitenanfang .

Titel vormerken Katalogdatensatz500177184

Vollanzeige Katalogdaten

Auf diesem Bildschirm erhalten Sie Katalog- und Exemplarinformationen zum ausgewählten Titel.

Im Bereich Kataloginformation werden die bibliographischen Details angezeigt. Per Klick auf Hyperlink-Begriffe wie Schlagwörter, Autoren, Reihen, Körperschaften und Klassifikationen können Sie sich weitere Titel des gewählten Begriffes anzeigen lassen.

Der Bereich Exemplarinformationen enthält zum einen Angaben über den Standort und die Verfügbarkeit der Exemplare. Zum anderen haben Sie die Möglichkeit, ausgeliehene Exemplare vorzumerken oder Exemplare aus dem Magazin zu bestellen.