Design, Implementation and Evaluation of the SENECA Spoken Language Dialogue System

Abstract

This chapter describes a speech-based user interface to a wide range of entertainment, navigation and communication applications in mobile environments by means of human-machine dialogues. The system has been developed in the framework of the EU project SENECA. It uses noise reduction, speech recognition and dialogue processing techniques. An interesting aspect relies in the fact that speech recognition results with low confidence and word-level ambiguities are compensated by engaging flexible clarification dialogues with the user. The SENECA system has been evaluated by means of user tests. With speech input, road safety, especially for complex tasks is significantly improved. The feeling of being distracted from driving is smaller with speech input than with manual input.