Carnegie Mellon University's objective is to create technology for real-time unlimited vocabulary spoken language processing in the context of practical applications. Our long-term goals continues to be the enhancement of the accuracy, robustness, portability, scalability and utility of spoken language systems, through the development of strategies to automatically acquire knowledge at all levels of the process and through unification of structures to represent this knowledge.

Carnegie Mellon pursues a broad program of research in the context of practical applications of value to the Department of Defense. Three application systems currently development draw on this work: (1) A speech interface for a wearable computer that provides access to information resources for the mobile warfighter. (2) The News on Demand system that uses speech recognition for automatic indexing of broadcast materials and for subsequent retrieval. (3) DIPLOMAT , a flexible multi-modal speech-to-speech translation system. Each application focusses on a currently difficult of aspect of speech technology.

Project Summary