No abstract

No abstract

No abstract

In this demonstration we present a mixedinitiative dialog system for address recognition that lets users to specify a complete addresses in a single sentence with address components spoken in their natural sequence. Users can also specify fewer address components in several ways, based on their convenience. The system extracts specified address components, prompts for missing information, disambiguates items independently or collectively all the while guiding the user so as to obtain the desired valid address. The language modeling and dialog management techniques developed for this purpose are also briefly described. Finally, several use cases with screen shots are presented. The combined system yields very high task completion accuracy on user tests.

This paper outlines the background development of “intelligent” technologies such as speech recognition. Despite significant progress in the development of these technologies, they still fall short in many areas, and rapid advances in areas such as dictation are actually stalled. In this paper we have proposed semi-automatic solutions — smart integration of human and intelligent efforts. One such technique involves improvement to the speech recognition editing interface, thereby reducing the perception of errors to the viewer. Other techniques that are described in the paper are batch enrollment, which allows the user to reduce the amount of time required for enrollment, and content spotting, which can be used for applications that have repeated content flow, such as movies or museum tours. The paper also suggests a general concept of distributive training of speech recognition systems that is based on data collection across a network.