Building a Robust System for Multimodal Emotion Recognition

Wagner, Johannes; Lingenfelser, Florian; André, Elisabeth

doi:10.1002/9781118910566.ch15

Cited by 9 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we will investigate how to speed up the input of emotional states in order to enable users to produce prosodic speech in daily environments. One idea would be exploit other modalities, such as facial expressions, to determine the user's emotional state based on our previous work on automated emotion recognition (Wagner et al 2015) and enhance the user's emotional expression by prosodic speech. Furthermore, it would be desirable to offer speech output to the participants that conveys not only emotions in a convincing manner, but also matches their personality.…”

Section: Resultsmentioning

confidence: 99%

Progress to a VOCA with Prosodic Synthesised Speech

Wülfing

André

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

Progress to a VOCA with Prosodic Synthesised Speech

Wülfing

André

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, interaction technology has to be used with caution in cars to not distract the driver. However, we believe that sensing technologies for automatically recognizing stress, and classifying emotions and activities (e.g., [10,12,20]) could improve a traffic companions impact on wellbeing. Also addressing other Positive Computing factors could help to increase wellbeing.…”

Section: Discussionmentioning

confidence: 99%

Traeddy

Martin

Geiger

Götz

et al. 2018

Proceedings of the Workshop on Human-Habitat for Health (H3): Human-Habitat Multimodal Interaction for Promoting Health and Wel

Self Cite

View full text Add to dashboard Cite

Commuting by car can be stressful, especially unexpected traffic jams may result in feelings of loss of control and social disconnectedness. In this paper, we present Traeddy, a teddy bear augmented with embedded technology, which serves as a wellbeing companion for car commuters in case of traffic jams. Traeddy is capable to help, for example by notifying relevant contacts about traffic jams and potential delays. We describe in detail the design process, including 20 contextual inquiries and report the evaluation of Traeddy through an online survey with 102 participants and a field study evaluating Traeddy with three commuters and two contacts in the field. The results of the field study indicate that Traeddy has a positive impact on the relationship between the commuter and the notified contact. Furthermore, the majority of the online participants anticipated Traeddy to be useful and to support their wellbeing in traffic jams.

show abstract

“…The classifiers are trained following [29], which allows training AU classifiers using datasets with a reduced amount of ground truth (only prototypical facial expressions are needed). Extraction of paralinguistic affective cues is done following [33]. Extracted facial and paralinguistic cues are combined through fusion strategies in order to generate a final prediction.…”

Section: Multimodal Communication Analysismentioning

confidence: 99%

KRISTINA: A Knowledge-Based Virtual Conversation Agent

Wanner

André

Blat

et al. 2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We present an intelligent embodied conversation agent with linguistic, social and emotional competence. Unlike the vast majority of the state-of-the-art conversation agents, the proposed agent is constructed around an ontology-based knowledge model that allows for flexible reasoning-driven dialogue planning, instead of using predefined dialogue scripts. It is further complemented by multimodal communication analysis and generation modules and a search engine for the retrieval of multimedia background content from the web needed for conducting a conversation on a given topic. The evaluation of the 1st prototype of the agent shows a high degree of acceptance of the agent by the users with respect to its trustworthiness, naturalness, etc. The individual technologies are being further improved in the 2nd prototype.

show abstract

Building a Robust System for Multimodal Emotion Recognition

Cited by 9 publications

References 53 publications

Progress to a VOCA with Prosodic Synthesised Speech

Progress to a VOCA with Prosodic Synthesised Speech

Traeddy

KRISTINA: A Knowledge-Based Virtual Conversation Agent

Contact Info

Product

Resources

About