IDENTIFYING AUDIO CONTENT USING DISTORTED TARGET PATTERNS

• US 20090254343A1
• Filed: 04/04/2008
• Published: 10/08/2009
• Est. Priority Date: 04/04/2008
• Status: Active Grant

• Current Assignee: Intuit, Inc.
• Original Assignee: Intuit, Inc.
• Inventors: Hart, Matt E.
• Granted Patent: US 8,615,397 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G10L 15/065 Adaptation

Abstract

Embodiments of a system for identifying audio content are described. During operation, the system receives a data stream from an electronic device via a communication network. Then, the system distorts a set of target patterns which are used to identify the audio content based on characteristics of the electronic device and/or the communication network. Next, the system identifies the audio content in the data stream based on the set of distorted target patterns.

Claims

1. A method for identifying audio content, comprising:

receiving a data stream from an electronic device via a communication network;

distorting a set of target patterns for identifying the audio content based characteristics of the electronic device and the communication network; and

identifying the audio content in the data stream based on the set of distorted target patterns.

2. The method of claim 1, wherein the electronic device includes a cellular telephone;

and

wherein the communication network includes a cellular-telephone network.

3. The method of claim 1, wherein communication via the communication network involves wireless communication.

4. The method of claim 1, wherein the audio content includes spoken information.

5. The method of claim 4, further comprising transcribing the audio content into text.

6. The method of claim 5, further comprising associating the text with a financial transaction.

7. The method of claim 6, wherein financial software performs the association.

8. The method of claim 7, wherein the financial software includes payroll software, income-tax software, accounting software, or customer-relationship-management software.

9. The method of claim 1, wherein the set of target patterns corresponds to a dictionary of words.

10. The method of claim 1, wherein distorting the set of target patterns includes changing an amplitude at a given frequency in a range of audio frequencies associated with the set of target patterns.

11. The method of claim 1, wherein the set of target patterns is distorted using a filter.

12. The method of claim 1, wherein the set of target patterns is distorted using an encoding technique.

13. The method of claim 1, wherein the set of target patterns is distorted based on characteristics associated with a user of the electronic device.

14. The method of claim 1, wherein the distortion of the set of target patterns includes dynamic distortion.

15. The method of claim 14, wherein the distortion is based on a confidence metric associated with the process of identifying the audio content.

16. The method of claim 14, wherein the distortion is based on a dynamic characteristic of the data stream.

17. The method of claim 14, wherein the distortion is based on training data that is included in the data stream.

18. The method of claim 17, wherein the training data includes audio data for predetermined frequencies.

19. The method of claim 17, wherein the training data is associated with a predetermined phrase.

20. The method of claim 17, wherein the training data is associated with a predetermined key-pad pattern on the electronic device.

21. The method of claim 17, wherein the training data is provided by the electronic device.

22. A computer-program product for use in conjunction with a computer system, the computer-program product comprising a computer-readable storage medium and a computer-program mechanism embedded therein for configuring the computer system, the computer-program mechanism including:

instructions for receiving a data stream from an electronic device via a communication network;

instructions for distorting a set of target patterns for identifying the audio content based on characteristics of the electronic device and the communication network; and

instructions for identifying audio content in the data stream based on the set of distorted target patterns.

23. The computer-program product of claim 22, wherein the electronic device includes a cellular telephone;

and

wherein the communication network includes a cellular-telephone network.

24. The computer-program product of claim 22, wherein the audio content includes spoken information.

25. The computer-program product of claim 24, further comprising transcribing the audio content into text.

26. The computer-program product of claim 25, further comprising associating the text with a financial transaction.

27. The computer-program product of claim 22, wherein the set of target patterns corresponds to a dictionary of words.

28. The computer-program product of claim 22, wherein the set of target patterns is distorted based on characteristics associated with a user of the electronic device.

29. The computer-program product of claim 22, wherein the distortion of the set of target patterns includes dynamic distortion.

30. The computer-program product of claim 29, wherein the distortion is based on training data that is included in the data stream.

31. A computer system, comprising:

a processor;

memory;

a program module, wherein the program module is stored in the memory and configured to be executed by the processor, the program module including;

instructions for receiving a data stream from an electronic device via a communication network;

instructions for distorting a set of target patterns for identifying the audio content based on characteristics of the electronic device and the communication network; and

instructions for identifying audio content in the data stream based on the set of distorted target patterns.