Robust Architecture for Human Language Technology

Technological advancements in the past few decades have made the spoken language technology systems very complex. This leads to a need for robust, portable and flexible platforms on which these spoken language technologies can be implemented. The development of the DARPA communicator system was a significant step in this direction and has fueled the design and development of impressive human language technology applications. Its distributed framework has offered numerous benefits to the research community, including reduced prototype development time, sharing of components across sites, and provision of a standard evaluation platform. It has also enabled development of client-server applications with complex inter-process communication between modules. However, this latter feature, though beneficial, introduces complexities which reduce overall system robustness to failure. In addition, the ability to handle multiple users and multiple applications from a common interface is not innately supported. In this paper, we describe our enhancements to the original communicator architecture to address robustness issues and to support multiple applications simultaneously