Ontology and parser dependencies approach for spoken dialogue system

In this paper, we propose a mobile spoken dialogue system (MOBILE SDS) based on parser dependencies and ontology. The turn (semantic) analysis algorithm integrated in the spoken dialogue understanding (SLU) module uses, at each turn of the dialogue, the dependencies generated by Stanford parser and a domain ontology to analyze the sentence and extract user's intention and slots values (i.e. user dialogue acts, concepts and their values). The SLU maps the sentence into a structure. The dialogue manager receives this mapping structure from the SLU module and chooses the action to be taken by the system. The MOBILE SDS was developed as a remote system on a mobile phone. It uses Google server for recognition and Google text to speech for speech synthesis provided with Android system. Dialogue understanding, dialogue managing and text generating modules reside on a remote computer. Ten volunteers' users have tested our system and a score of 3.6 on Likert scale was obtained.