Systems and Methods of Performing Speech Recognition with Barge-In for use in a Bluetooth System

• US 20090132255A1
• Filed: 11/19/2007
• Published: 05/21/2009
• Est. Priority Date: 11/19/2007
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Lu, Younan
• Granted Patent: US 8,112,280 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts

Abstract

Embodiments of the present invention improve methods of performing speech recognition with barge-in. In one embodiment, the present invention includes a speech recognition method comprising starting a synthesis of recorded speech, receiving a user speech input signal providing information regarding a user choice, detecting an initial portion of the user speech input signal, selectively altering the synthesis of recorded speech, and recognizing the user choice.

Claims

1. An apparatus including an electronic device, the electronic device comprising:

a processor comprising;

a speech synthesizer; and

a speech recognizer including a recognition set;

an analog to digital converter coupled to receive an analog speech input signal and provide corresponding digital speech data to the speech recognizer;

a digital to analog converter coupled to receive synthesized speech data from the speech synthesizer and provide a corresponding analog speech output signal; and

a nonvolatile memory coupled to provide recorded voice prompt data to the speech synthesizer, the nonvolatile memory comprising;

data corresponding to a plurality of recorded voice prompts,

wherein the processor selectively alters the speech synthesizer.

2. The apparatus of claim 1 wherein the nonvolatile memory is flash memory.

3. The apparatus of claim 1 wherein the data corresponding to a plurality of recorded voice prompts includes wave files.

4. The apparatus of claim 1 wherein the speech synthesizer includes volume control.

5. The apparatus of claim 1 wherein the speech synthesizer includes on-off control.

6. The apparatus of claim 1 wherein the electronic device is a portable electronic device.

7. The apparatus of claim 1 wherein the electronic device is enabled to communicate over a wireless personal area network.

8. The apparatus of claim 1 wherein the electronic device is a wireless headset.

9. The apparatus of claim 1 wherein the processor selectively alters the speech recognizer.

10. The apparatus of claim 9 wherein the speech recognizer employs a selectively enabled echo canceller.

11. The apparatus of claim 9 wherein the speech recognizer employs a selectively enabled voice recognition threshold adjuster.

12. A speech recognition method comprising:

starting a synthesis of recorded speech to prompt a user to communicate a user choice, wherein an element in a recognition set corresponds to the user choice;

receiving a user speech input signal providing information regarding the user choice;

detecting an initial portion of the user speech input signal;

selectively altering the synthesis of recorded speech in response to detecting the initial portion of the user speech input signal; and

recognizing the user choice, wherein the recognizing includes determining the element in the recognition set which corresponds to the user choice.

13. The method of claim 12 wherein the synthesis of recorded speech includes piping a wave file.

14. The method of claim 12 wherein selectively altering the synthesis of recorded speech includes changing the volume.

15. The method of claim 12 wherein selectively altering the synthesis of recorded speech includes muting the sound.

16. The method of claim 12 wherein the synthesis includes transferring packets of synthesis data, wherein selectively altering the synthesis of recorded speech includes dropping at least one packet of the packets of synthesis data.

17. The method of claim 12 wherein the selectively altering the synthesis of recorded speech includes substituting alternate synthesis data.

18. The method of claim 12 further comprising selectively altering the recognizing in response to detecting the initial portion of the user speech input signal.

19. The method of claim 18 wherein selectively altering the recognizing includes providing echo cancelling.

20. The method of claim 18 wherein selectively altering the recognizing includes changing the voice recognition threshold.

21. A speech recognition method comprising:

starting a synthesis of recorded speech to prompt a user to communicate a user choice, wherein an element in a recognition set corresponds to the user choice;

receiving a user speech input signal providing information regarding the user choice;

detecting an initial portion of the user speech input signal;

selectively altering the recognizing in response to detecting the initial portion of the user speech input signal; and

recognizing the user choice, wherein the recognizing includes determining the element in the recognition set which corresponds to the user choice.

22. The method of claim 21 wherein selectively altering the recognizing includes providing echo cancelling.

23. The method of claim 21 wherein selectively altering the recognizing includes changing the voice recognition threshold.