Conversational agent for mobile-learning: A review and a proposal of a multilanguage text-to-speech agent, “MobiSpeech”

The new Information, communication, and mobile technologies empower the users to learn anywhere and anytime. They also need conversational systems that could be aware of their mobile context in order to adjust it dynamically. The actual research field is focusing on adaptive conversational systems, especially in the case of Mobile-learning. This paper presents a comparative study of some related works. Then, it proposes an M-learning architecture based on hybrid cooperative agents (mobile, conversational, cognitive), with the possibility integrating Multi-Language ontology for the development of a Conversational Agent (CA) speaking Multi-Language especially Arabic language. A prototype of text-to-speech mobile agent (MobiSpeech) is presented and discussed. MobiSpeech is intended for mobile users, and provide all services to read any text and any text file extension for the user while considering the existing context-awareness.