The Speech Recognition Virtual Kitchen: An Initial Prototype

摘要

This paper describes a "kitchen" environment to promote community sharing of research techniques, foster innovative experimentation, and provide solid reference systems as a tool for education, research, and evaluation with a focus on, but not restricted to, speech and language research. The core of the research infrastructure is the use of virtual machines (VMs) that provide a consistent environment for experimentation. We liken the virtual machines to a "kitchen" because they provide the infrastructure into which one can install "appliances" (e.g., speech recognition toolkits), "recipes" (scripts for creating state-of-the art systems), and "ingredients" (language data). In this demo, we show an initial proposal for a community framework based on VM technology used for teaching classes at CMU and OSU.