Abstract: Described is a method for retrieving task information using task-based indexes. The method includes an act of acquiring task-based categories and documents. Task-descriptive symbols are then associated with each task-based category. The documents are indexed to create an index having index words and pointers. The index words reflect the information in the documents and the pointers connect particular index words to particular documents or subparts of documents. The task-descriptive symbols are correlated with the index words to create an alignment of words having similar meaning such that index words are matched with similar task-descriptive symbols. The task-based indexes are formed by grouping the alignment of words with the respective task-based category. A user may use the task-based index by inputting task descriptive symbols into the task-based index to retrieve a document having task information pertaining to the task-descriptive symbols.

Abstract: Methods and apparatus are provided for speech-based data retrieval from a portable communication device, such as a cell phone with an onboard dataset. The method comprises semantically indexing the dataset with domain related keywords that are intuitive to a user familiar with the dataset domain. When the user speaks a keyword, a speech recognition system within the portable device links the keyword to a semantically related data file in the dataset. A processor in the portable communication device retrieves the selected data and converts it for presentation on a visual display and/or an audio output.