BACKGROUND SPEECH RECOGNITION ASSISTANT

• US 20130080171A1
• Filed: 09/27/2011
• Published: 03/28/2013
• Est. Priority Date: 09/27/2011
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Mozer, Todd F., Verneulen, Pieter J.
• Granted Patent: US 8,996,381 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

In one embodiment, a method receives an acoustic input signal at a speech recognizer configured to recognize the acoustic input signal in an always on mode. A set of responses based on the recognized acoustic input signal is determined and ranked based on criteria. A computing device determines if the response should be output based on a ranking of the response. The method determines an output method in a plurality of output methods based on the ranking of the response and outputs the response using the output method if it is determined the response should be output.

Claims

1. A method comprising:

receiving an acoustic input signal at a speech recognizer configured to recognize the acoustic input signal in an always on mode;

determining a set of responses based on the recognized acoustic input signal;

ranking the set of responses based on criteria;

determining, by a computing device, if the response should be output based on a ranking of the response;

determining an output method in a plurality of output methods based on the ranking of the response; and

outputting the response using the output method if it is determined the response should be output.

2. The method of claim 1, wherein the response is outputted without touching computing device or speaking a “

trigger”

phrase to active the speech recognizer.

3. The method of claim 1, further comprising:

classifying portions of the acoustic input signal into different classifications;

selecting the classification based on a criterion associated with the classification; and

using the classification to determine the set of responses.

4. The method of claim 3, wherein the criterion comprises a frequency, an order, or a distance in time.

5. The method of claim 1, wherein classifying portions comprises analyzing the acoustic input signal for a set of keywords associated with the different classifications.

6. The method of claim 1, wherein the ranking is based on a relevance factor, urgency factor, and an importance factor assigned to the response.

7. The method of claim 1, wherein the output method is determined based on a relevance factor, urgency factor, and an importance factor assigned to the response.

8. The method of claim 1, further comprising:

storing information in memory based on the recognized acoustic input signal; and

recalling the stored information at a later time to determine the set of responses.

9. The method of claim 1, wherein:

a first stage recognizer is configured to recognize the acoustic input signal in the always on mode and classify portions of the acoustic input signal into different classifications using a first speech recognition algorithm;

a second stage recognizer is triggered based on the selection of the classification, wherein the second stage recognizer is configured to use a second speech recognition algorithm different from the first speech recognition algorithm to recognize the acoustic input signal.

10. A method comprising:

receiving an acoustic input signal at a first stage recognizer, the first stage recognizer being configured to recognize the acoustic input signal in an always on mode;

classifying, by a computing device, portions of the acoustic input signal into different classifications using a first speech recognition algorithm;

determining a second stage recognizer should be triggered based on a selection of a classification based on classified portions being classified with the selected classification; and

triggering the second stage recognizer to turn on to recognize the acoustic input signal, the second stage recognizer configured to use a second speech recognition algorithm different from the first speech recognition algorithm to recognize the acoustic input signal.

11. The method of claim 10, wherein the first stage recognizer uses a vocabulary that is smaller than a vocabulary used by the second stage recognizer.

12. The method of claim 10, wherein the first stage recognizer uses less memory and computer processing unit (CPU) cycles than the second stage recognizer.

13. The method of claim 10, further comprising:

causing the second stage recognizer to turn on upon receiving the trigger to recognize the acoustic input signal, wherein the second stage recognizer is configured to output a response based on recognition of the acoustic input signal.

14. The method of claim 10, wherein the first stage recognizer operates in a lower power mode than the second stage recognizer.

15. A method comprising:

receiving a signal from a first stage recognizer based on recognition of an acoustic input signal and classification of portions of the acoustic input signal into a classification in a plurality of classifications using a first speech recognition algorithm, the first stage recognizer being configured to recognize the acoustic input signal in an always on mode;

activating, by a computing device, the second stage recognizer upon receiving the signal to recognize the acoustic input signal, the second stage recognizer configured to use a second speech recognition algorithm;

determining a response to the recognized acoustic input signal;

determining if the response should be output based on a ranking of the response; and

outputting the response if it is determined the response should be output.

16. The method of claim 15, wherein determining the response comprises:

determining a plurality of responses based on the recognized acoustic input signal;

ranking the plurality of responses based on criteria; and

selecting a response based on the ranking.

17. The method of claim 16, wherein a response is not selected to be output if a ranking threshold for any of the plurality of responses is not achieved.

18. The method of claim 15, wherein the ranking is based on a relevance factor, urgency factor, and an importance factor assigned to the response.

19. The method of claim 15, further comprising:

determining an output method in a plurality of output methods based on the ranking; and

outputting the response based on the output method.

20. The method of claim 15, wherein the acoustic input signal is received through a network from the first stage recognizer.

21. A system comprising:

a first stage recognizer configured to recognize the acoustic input signal using a first speech recognition algorithm in an always on mode, the first stage recognizer configured to;

receive an acoustic input signal;

classify portions of the acoustic input signal into different classifications using a first speech recognition algorithm;

determine a second stage recognizer should be triggered based on a selection of a classification based on classified portions being classified with the selected classification; and

a second stage recognizer configured to;

receive a signal from the first stage recognizer to activate the second stage recognizer;

activate the second stage recognizer upon receiving the signal to recognize the acoustic input signal, the second stage recognizer configured to use a second speech recognition algorithm different from the first speech recognition algorithm to recognize the acoustic input signal;

determine a response to the recognized acoustic input signal;

determine if the response should be output based on a ranking of the response; and

output the response if it is determined the response should be output.

22. The system of claim 21, wherein the first stage recognizer and the second stage recognizer are located in a same device.

23. The system of claim 22, wherein:

the device includes a processor and memory,

the first stage recognizer uses less memory and less processing cycles of the processor during speech recognition.

24. The system of claim 21, wherein the first stage recognizer is located in a first device and the second stage recognizer are located in a second device.

25. The system of claim 24, wherein the first device receives the acoustic input signal and sends the acoustic input signal to the second device over a network.