The Speech Recognition Virtual Kitchen Toolkit

Speech recognition and natural language processing are interesting and relevant applications of many CS principles. Unfortunately, the barrier to entry for using existing tools is quite high, often requiring many hours installing, compiling, testing, and debugging tools before students can even begin exploring the technical concepts. The "Speech Recognition Virtual Kitchen" environment is an NSF-sponsored collaborative research infrastructure project that has the goals to promote community sharing of research techniques, foster innovative experimentation, and provide solid reference systems as a tool for education, research, and evaluation. The core of the research infrastructure is the use of virtual machines (VMs) that provide a consistent experimental environment. We liken the virtual machines to a "kitchen" because they provide the infrastructure into which one can install "appliances" (e.g., speech recognition tool-kits), "recipes" (scripts for creating state-of-the art systems), and "ingredients" (language data). A web-based community platform allows physically disconnected users to jointly explore VMs, learn from each other, and collaborate in research. This demo will provide an overview of available VMs, suggestions for use in undergraduate and graduate computer science courses and capstone projects, and a demonstration of our teaching VM, highlighting the ease of working with available tools. We invite participation in our community through downloading and uploading VMs, which can be an entry to open-source software development. More information can be found at speechkitchen.org.