Alle Publikationen
- <<
- <
- 1
2013
-
(2013): A cross-cultural, multimodal, affective corpus for gesture expressivity analysis. In: Journal on Multimodal User Interfaces 7 (1-2), S. 121-134. DOI: 10.1007/s12193-012-0112-x
Abstract: A multimodal, cross-cultural corpus of affective behavior is presented in this research work. The corpus construction process, including issues related to the design and implementation of an experiment, is discussed along with resulting acoustic prosody, facial expressions and gesture expressivity features. However, research work presented here focuses more on the cross-cultural aspect of gestural behavior defining a common corpus construction protocol aiming to identify cultural patterns within non-verbal behavior across cultures i.e. German, Greek and Italian. Culture specific findings regarding gesture expressivity are derived from the affective analysis performed. Additionally, the multimodal aspect, including prosody and facial expressions, is researched in terms of fusion techniques. Finally, a release plan of the corpus to the public domain is discussed aiming to establish the current corpus as a benchmark multimodal, cross-cultural standard and reference point.
2008
-
(2008): Private emotions versus social interaction. A data-driven approach towards analysing emotion in speech. In: User Modeling and User-Adapted Interaction 18 (1-2), S. 175-206. DOI: 10.1007/s11257-007-9039-4
Abstract: The 'traditional' first two dimensions in emotion research are VALENCE and AROUSAL. Normally, they are obtained by using elicited, acted data. In this paper, we use realistic, spontaneous speech data from our 'AIBO' corpus (human-robot communication, children interacting with Sony's AIBO robot). The recordings were done in a Wizard-of-Oz scenario: the children believed that AIBO obeys their commands; in fact, AIBO followed a fixed script and often disobeyed. Five labellers annotated each word as belonging to one of eleven emotion-related states; seven of these states which occurred frequently enough are dealt with in this paper. The confusion matrices of these labels were used in a Non-Metrical Multi-dimensional Scaling to display two dimensions; the first we interpret as VALENCE, the second, however, not as AROUSAL but as INTERACTION, i.e., addressing oneself (angry, joyful) or the communication partner (motherese, reprimanding). We show that it depends on the specifity of the scenario and on the subjects' conceptualizations whether this new dimension can be observed, and discuss impacts on the practice of labelling and processing emotional data. Two-dimensional solutions based on acoustic and linguistic features that were used for automatic classification of these emotional states are interpreted along the same lines.
Keywords: AIBO, annotation, Arousal, categories, Communication, data-driven, deutsche Community, dimensions, emotion, emotion research, Emotionserkennung, Emotionssensitive Systeme, Interaction, Interaktionspartner, Kognitionswissenschaft/Social Sciences/Humanities, Kommunikation, Mensch oder Maschine, Mensch-Technik-Relationen (MTR), non-metrical multi-dimensional scaling, Psychologie, Rolle von Emotion, Realtechnik, script, Soziosensitive Systeme, speech, Technik, Valence 2003
-
(2003): Konzeptframes und Relationen. Extraktion, Annotation und Analyse französischer Corpora aus dem World Wide Web. Zugl.: Hamburg, Univ., Diss., 2003. Berlin: Akad. Verl.-Ges. Aka (Dissertationen zur künstlichen Intelligenz)
Abstract: "Konzeptframes und Relationen" untersucht den Zusammenhang zwischen Wissen, Wissensrepräsentation und sprachlichen Corpora am Beispiel der Extraktion von französischen Textabschnitten aus dem Web. Interpretationen der Corpora werden in aussagekräftigen und allgemeinen linguistischen Strukturen angeordnet: den Konzeptframes. Die automatische Erhebung von semantischen Umgebungen von Lexemen aus dem Netz rückt die Linguistik näher heran an die Empirie und weiter weg von der Beispiele-Linguistik; durch die systematische Anordnung und Auswertung des Weltwissens erfährt der Terminus eine überzeugende Integration in die lexikalische Semantik. Vorgestellt werden die automatischen Extraktionsmethoden, das computerunterstützte Annotationsverfahren mit Hilfe einer linguistisch motivierten Ontologie und die Auswertungen der Ergebnisse. Letztere betreffen u. a. den Ausbau der verwendeten Ontologie, die Aufstellung von Mustern des sprachlichen Ausdrucks von Relationen in Corpora, die Entwicklung und Interpretation intrakonzeptueller Strukturen und die Umwandlung der gesammelten Wissensbestände in ein Format für das Semantic Web. Darüber hinaus gibt die Arbeit einen Überblick über weitere Arbeiten auf den relevanten Gebieten
- <<
- <
- 1