Robust Speech Understanding for Multi-Modal Human-Robot Communication

Hüwel, Sonja; Wrede, Britta; Sagerer, Gerhard

doi:10.1109/roman.2006.314393

Cited by 17 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hüwel et al [52] propose the concept of Situated Semantic Unit: these meaning atoms are extracted from sentences and expose semantic links to other units. The parser tries to satisfy these links and rate accordingly the semantic interpretation of the sentence.…”

Section: Related Workmentioning

confidence: 99%

Grounding the Interaction: Knowledge Management for Interactive Robots

Lemaignan

2013

Künstl Intell

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Grounding the Interaction: Knowledge Management for Interactive Robots

Lemaignan

2013

Künstl Intell

View full text Add to dashboard Cite

“…Speech is recognized by the ESMERALDA speech recognizer [18], with speakerindependent acoustic model, and a situated speechunderstanding component [19].…”

Section: Perceptual Analysismentioning

confidence: 99%

The curious robot - Structuring interactive robot learning

Lütkebohle

Peltason

Schillingmann

et al. 2009

2009 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-If robots are to succeed in novel tasks, they must be able to learn from humans. To improve such humanrobot interaction, a system is presented that provides dialog structure and engages the human in an exploratory teaching scenario. Thereby, we specifically target untrained users, who are supported by mixed-initiative interaction using verbal and non-verbal modalities. We present the principles of dialog structuring based on an object learning and manipulation scenario. System development is following an interactive evaluation approach and we will present both an extensible, eventbased interaction architecture to realize mixed-initiative and evaluation results based on a video-study of the system. We show that users benefit from the provided dialog structure to result in predictable and successful human-robot interaction.

show abstract

“…The semantics of the utterances is often also hard-coded. An interesting corpus-based approach has been used for the BIRON robot (Hüwel, Wrede and Sagerer 2006). A large set of so-called 'situated semantic units' (SSU) was designed based on a corpus of situated conversational data.…”

Section: Robots With Languagementioning

confidence: 99%

“…In the CARL robot, a combination of deep and shallow parsing is used to cope with non-grammatical sentences (Seabra Lopes, Teixeira, Quinderé and Rodrigues 2008). In BIRON, interpretations are rated by semantic coherence, which may in part be evaluated in the situated context, rather than by grammatical correctness (Hüwel et al 2006).…”

Section: Robots With Languagementioning

confidence: 99%