0000000000390322
AUTHOR
Yuichiro Yoshikawa
A Topic Recognition System for Real World Human-Robot Conversations
One of the main features of social robots is the ability to communicate and interact with people as partners in a natural way. However, achieving a good verbal interaction is a hard task due to the errors on speech recognition systems, and due to the understanting the natural language itself. This paper tries to overcome such kind of problems by presenting a system that enables social robots to get involved in conversation by recognizing its topic. Through the use of classical text mining approach, the presented system allows social robots to understand topics of conversation between human partners, enabling the customization of behaviours in their accordance. The system has been evaluated …
Towards Partners Profiling in Human Robot Interaction Contexts
Individuality is one of the most important qualities of humans. Social robots should be able to model the individuality of the human partners and to modify their behaviours accordingly.This paper proposes a profiling system for social robots to be able to learn the individuality of human partners in social contexts. Profiles are expressed in terms of of identities and preferences bound together. In particular, people’s identity is captured by the use of facial features, while preferences are extracted from the discussion between the partners. Both are bound using an Hebb network. Experiments show the feasibility and the performances of the approach presented.
A Multimodal People Recognition System for an Intelligent Environment
In this paper, a multimodal system for recognizing people in intelligent environments is presented. Users are identified and tracked by detecting and recognizing voices and faces through cameras and microphones spread around the environment. This multimodal approach has been chosen to develop a flexible and cheap though reliable system, implemented through consumer electronics. Voice features are extracted through a short time spectrum analysis, while face features are extracted using the eigenfaces technique. The recognition task is achieved through the use of some Support Vector Machines, one per modality, that learn and classify the features of each person, while bindings between modalit…
Audio-video people recognition system for an intelligent environment
In this paper an audio-video system for intelligent environments with the capability to recognize people is presented. Users are tracked inside the environment and their positions and activities can be logged. Users identities are assessed through a multimodal approach by detecting and recognizing voices and faces through the different cameras and microphones installed in the environment. This approach has been chosen in order to create a flexible and cheap but reliable system, implemented using consumer electronics. Voice features are extracted by a short time cepstrum analysis, and face features are extracted using the eigenfaces technique. The recognition task is solved using the same Su…