DialogStudio: A workbench for data-driven spoken dialog system development and management

Recently, data-driven speech technologies have been widely used to build speech user interfaces. However, developing and managing data-driven spoken dialog systems are laborious and time consuming tasks. Spoken dialog systems have many components and their development and management involves numerous tasks such as preparing the corpus, training, testing and integrating each component for system development and management. In addition, data annotation for natural language understanding and speech recognition is quite burdensome. This paper describes the development of a tool, DialogStudio, to support the development and management of data-driven spoken dialog systems. Desirable aspects of the data-driven spoken dialog system workbench tool are identified, and architectures and concepts are proposed that make DialogStudio efficient in data annotation and system development in a domain and methodology neutral manner. The usability of DialogStudio was validated by developing dialog systems in three different domains with two different dialog management methods. Objective evaluations of each domain show that DialogStudio is a feasible solution as a workbench for data-driven spoken dialog systems.