The system retrieves information from the internet using multiple search engines
that are simultaneously launched by the search engine commander. The commander
is responsive to a speech-enabled system including a speech recognizer and natural
language parser. The user speaks to the system in natural language requests, and
the parser extracts the semantic content from the user's speech, based on a set
of goal oriented grammars. The preferred system includes a fixed grammar and an
updatable or downloaded grammar, allowing the system to be used without extensive
training and yet capable of being customized for a particular user's purposes.
Results obtained from the search engines are filtered based on information extracted
from an electronic program guide and from prestored user profile data. The results
may be displayed on screen or through synthesized speech.
