LINGVO/LASER: Prototyping Concept of Dialogue Information System with Spreading Knowledge

The presented paper introduces a scalable modular prototyping concept and methodology framework for rapid development of domain-oriented dialogue information systems being developed at Laboratory of Intelligent Communication Systems (LICS). The whole system consists of two practically standalone aggregates of software modules and knowledge bases: A speech recognition and synthesis software—LASER, and a generic task-independent scalable dialogue information system—LINGVO. The article describes the architecture, design, and philosophy of the framework in details and discusses its benefits already experienced while used to build a voice-driven dialogue application.