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 verbalinteraction is a hard task due to the errors on speech recognition systems, and dueto the understanting the natural language itself. This paper tries to overcome suchkind of problems by presenting a system that enables social robots to get involvedin conversation by recognizing its topic. Through the use of classical text miningapproach, the presented system allows social robots to understand topics of conversation between human partners, enabling the customization of behaviours in theiraccordance. The system has been evaluated in different contexts, taking in accountthe quality and accuracy of the speech recognition syestem used by the social robot.
|Titolo della pubblicazione ospite||Intelligent Autonomous Systems 12|
|Numero di pagine||9|
|Stato di pubblicazione||Published - 2013|
Serie di pubblicazioni
|Nome||ADVANCES IN INTELLIGENT SYSTEMS AND COMPUTING|
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Computer Science(all)
Sorbello, R., Ishiguro, H., Anzalone, S. M., Pagello, E., Menegatti, E., & Yoshikawa, Y. (2013). A Topic Recognition System for Real Word Human-Robot Conversations. In Intelligent Autonomous Systems 12 (pagg. 383-391). (ADVANCES IN INTELLIGENT SYSTEMS AND COMPUTING).