Method for speech-based data retrieval on portable devices

• US 7,275,049 B2
• Filed: 06/16/2004
• Issued: 09/25/2007
• Est. Priority Date: 06/16/2004
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Clausner, Timothy C., Hadley, Brent L.
• Primary Examiner(s): Hirl; Joseph P
• Assistant Examiner(s): Holmes; Michael B.
• Application Number:
  US10/870,880
• Publication Number:
  US 20050283369A1
• Time in Patent Office: 1,196 Days
• Field of Search: 706/55
• US Class Current: 706/55
• CPC Class Codes: G06F 16/38 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

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.

Claims

1. A method of speech-based data retrieval from a portable communication device having access to a plug-in memory card dataset that has been semantically indexed for a non-natural language topical domain, comprising the steps of:

a) converting one or more spoken keywords related to the non-natural language topical domain into a query word signal;

b) linking the query word signal to one or more related index words stored in the semantically indexed plug-in memory card dataset;

c) retrieving a data file stored in the semantically indexed plug-in memory card dataset that is associated with the one or more linked index words; and

d) processing the retrieved data file for presentation.

2. The method of claim 1 wherein semantic indexing of a non-natural language subset of the dataset comprises associating a list of m index words (w^Tn₁, w^Tn₂, . . . w^Tn_m) with a corresponding data file T_n.

3. The method of claim 2 wherein each of the m index words has an association with the non-natural language data in file T_n.

4. The method of claim 1 wherein the linking step comprises associating the query word signal with index words that are related in meaning to the query word signal.

5. The method of claim 1 wherein the processing step comprises generating a visual display of the retrieved data file.

6. The method of claim 1 wherein the processing step comprises generating an audible output of the retrieved data file.

7. A speech-based portable communication device, comprising:

an accessible dataset having semantically indexed data files related to a lexicon of keywords, wherein the dataset is implemented on a plug-in memory card;

a speech recognition and search system configured to link one or more of the lexicon of keywords to semantically related non-natural language data in the accessible dataset;

a processor configured to retrieve the keyword-linked data from the accessible dataset and to process the retrieved data for presentation; and

an output device configured to receive the processed data from the processor and to present the processed data.

8. The portable communication device of claim 7 wherein the speech recognition and search system is activated by human speech.

9. The portable communication device of claim 7 wherein the output device is configured to present the processed data as a visual display.

10. The portable communication device of claim 7 wherein the output device is configured to present the processed data in audible form.

11. The portable communication device of claim 7 wherein the lexicon of keywords is intuitively related to the semantic index of data files in the accessible dataset.

12. The portable communication device of claim 7 wherein the accessible dataset comprises a non-natural language topical domain.

13. The portable communication device of claim 7 wherein the accessible dataset is configured to communicate with the portable communication device via a remote network.

14. The portable communication device of claim 13 wherein the remote network is a wireless network.

15. A method of speech-based data retrieval from a portable communication device having access to a plug-in memory card dataset that has been semantically indexed for a non-natural language topical domain, comprising the steps of:

a) converting one or more spoken keywords related to the non-natural language topical domain into a query word signal;

b) linking the query word signal to synonyms of one or more related index words stored in the semantically indexed plug-in memory card dataset;

c) linking the synonyms of the one or more related index words to their respective one or more related index words;

d) retrieving a data file stored in the semantically indexed plug-in memory card dataset that is associated with the one or more related index words; and

e) processing the retrieved data file for presentation.