Target keyword selection

1. A method of operating an automatic speech recognition (ASR) system in a mobile device, the method comprising:

collecting keyword candidates;

collecting usage frequency data for keywords in the keyword candidates;

collecting situational usage frequency data for the keywords in the keyword candidates;

selecting target keywords from the keyword candidates based on the usage frequency data and the situational usage frequency data;

detecting, by a keyword detector of the mobile device, one or more of the target keywords in a voice command using continuous detection of the target keywords; and

processing, by the keyword detector, the voice command based on the detected one or more of the target keywords, including:

execution of the voice command in a case that the voice command, based on the detected one or more of the target keywords, is a keyword command executable by the keyword detector; and

sending of the voice command to an ASR module of the mobile device for execution or further processing in a case that the voice command, based on the detected one or more of the target keywords, is not executable by the keyword detector.

2. The method of claim 1 , further comprising:

determining frequency scores for the keywords in the keyword candidates based on the usage frequency data and the situational usage frequency data.

3. The method of claim 2 , wherein the target keywords are selected based on the frequency scores.

4. The method of claim 1 , further comprising:

determining a confidence score for each of the detected one or more of the target keywords.

5. The method of claim 4 , further comprising:

processing each of the detected one or more of the target keywords when the confidence score is higher than a threshold.

6. The method of claim 5 , further comprising:

adjusting the threshold when a detection failure or false alarm occurs during the detection of the target keywords.

7. The method of claim 1 , further comprising:

storing the target keywords in a memory.

8. The method of claim 1 , wherein the keyword candidates comprise one or more of: names in a contact list, names of applications installed on the mobile device, common keywords or manually enrolled keywords.

9. The method of claim 1 , wherein the situational usage frequency data includes data related to situations surrounding the mobile device when the keywords in the keyword candidates were used on the mobile device.

10. A mobile device comprising:

a memory; and

a processor communicatively coupled to the memory, the processor configured to:

collect keyword candidates;

collect usage frequency data for keywords in the keyword candidates;

collect situational usage frequency data for the keywords in the keyword candidates;

select target keywords from the keyword candidates based on the usage frequency data and the situational usage frequency data;

detect, by a keyword detector of the processor, one or more of the target keywords in a voice command using continuous detection of the target keywords;

process, by the keyword detector, the voice command based on the detected one or more of the target keywords, including:

execution of the voice command in a case that the voice command, based on the detected one or more of the target keywords, is a keyword command executable by the keyword detector; and

sending of the voice command to an ASR module of the mobile device for execution or further processing in a case that the voice command, based on the detected one or more of the target keywords, is not executable by the keyword detector.

11. The mobile device of claim 10 , wherein the processor is configured to determine frequency scores for the keywords based on the usage frequency data and the situational usage frequency data.

12. The mobile device of claim 11 , wherein the target keywords are selected based on the frequency scores.

13. The mobile device of claim 10 , wherein the processor is configured to determine a confidence score for each of the detected one or more of the target keywords.

14. The mobile device of claim 13 , wherein the processor is configured to process each of the detected one or more of the target keywords when the confidence score is higher than a threshold.

15. The mobile device of claim 14 , wherein the processor is configured to adjust the threshold when a detection failure or false alarm occurs during the detection of the target keywords.

16. The mobile device of claim 10 , wherein the processor is configured to store the target keywords in the memory.

17. The mobile device of claim 10 , wherein the keyword candidates comprise one or more of: names in a contact list, names of applications installed on the mobile device, common keywords or manually enrolled keywords.

18. The mobile device of claim 10 , wherein the situational usage frequency data includes data related to situations surrounding the mobile device when the keywords in the keyword candidates were used on the mobile device.

19. A non-transitory computer-readable storage medium comprising code, which, when executed by a processor of a mobile device, causes the processor to operate an automatic speech recognition (ASR) system, the non-transitory computer-readable storage medium comprising:

code for collecting keyword candidates;

code for collecting usage frequency data for keywords in the keyword candidates;

code for collecting situational usage frequency data for the keywords in the keyword candidates;

code for selecting target keywords from the keyword candidates based on the usage frequency data and the situational usage frequency data;

code for detecting, by a keyword detector of the processor, one or more of the target keywords in a voice command using continuous detection of the target keywords; and

code for processing, by the keyword detector, the voice command based on the detected one or more of the target keywords, including:

execution of the voice command in a case that the voice command, based on the detected one or more of the target keywords, is a keyword command executable by the keyword detector; and

sending of the voice command to an ASR module of the mobile device for execution or further processing in a case that the voice command based on the detected one or more of the target keywords is not executable by the keyword detector.

20. The non-transitory computer-readable storage medium of claim 19 , further comprising:

code for determining frequency scores for the keywords in the keyword candidates based on the usage frequency data and the situational usage frequency data.

21. The non-transitory computer-readable storage medium of claim 20 , wherein the target keywords are selected based on the frequency scores.

22. The non-transitory computer-readable storage medium of claim 19 , further comprising:

code for determining a confidence score for each of the detected one or more of the target keywords; and

code for processing each of the detected one or more of the target keywords when the confidence score is higher than a threshold.

23. The non-transitory computer-readable storage medium of claim 19 , wherein the situational usage frequency data includes data related to situations surrounding the processor when the keywords in the keyword candidates were used.