Method of providing voice command and electronic device supporting the same

• US 9,934,781 B2
• Filed: 06/30/2015
• Issued: 04/03/2018
• Est. Priority Date: 06/30/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Subhojit, Chakladar, Lee, Sang Hoon, Lee, Ji Min
• Primary Examiner(s): Siddo, Ibrahim
• Application Number:
  US14/755,441
• Publication Number:
  US 20150379993A1
• Time in Patent Office: 1,008 Days
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

An electronic device, a method, and a chip set are provided. The electronic device includes a memory configured to store at least one of audio feature data of audio data and speech recognition data obtained by speech recognition of audio data; and a control module connected to the memory, wherein the control module is configured to update a voice command that is set to execute a function through voice, the function being selected based on at least one of the audio feature data, the speech recognition data, and function execution data executed in relation to the audio data.

Claims

1. An electronic device, comprising:

a memory which stores data; and

a control module operably connected to the memory,

wherein the control module is configured to;

collect audio data;

update a voice command that is set to execute a function through voice, wherein the updating is based on at least one of audio feature data extracted from the collected audio data, speech recognition data obtained by speech recognition of the collected audio data, or function execution data executed in relation to the collected audio data;

update a weight of at least one of the audio feature data, the speech recognition data, and the function execution data; and

if the updated weight satisfies a specific condition, perform one of;

generating a candidate recognition model with the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and updating a weight of an existing candidate recognition model according to the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and changing an existing candidate recognition model into a recognition model corresponding to a voice command;

or

updating a weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data and removing at least one of a candidate recognition model and a recognition model corresponding to the updated weight.

2. The electronic device of claim 1, wherein the control module is further configured to register a new voice command corresponding to the changed recognition model.

3. The electronic device of claim 1, wherein the control module is further configured to remove a registered voice command corresponding to the removed recognition model.

4. The electronic device of claim 1, wherein the control module is further configured to control a display to output at least one of the audio feature data, the speech recognition data, the function execution data, and the voice command.

5. The electronic device of claim 1, wherein the control module is further configured to control at least one of the weight update of the audio feature data on the basis of a frequency of occurrence of the audio feature data, the weight update of the speech recognition data on the basis of a frequency of occurrence of the speech recognition data, and the weight update of the function execution data using at least one of whether to execute a function of the function execution data and a function execution duration time of the function execution data.

6. The electronic device of claim 1, wherein the control module is further configured to control a communication interface that transmits the collected audio data to a server device and receives, from the server device, at least one of the audio feature data, the speech recognition data, and the function execution data.

7. The electronic device of claim 6, wherein the control module is further configured to control a communication interface that receives, from the server device, a voice command generated based on at least one of the audio feature data, the speech recognition data, and the function execution data.

8. A voice command providing method, comprising:

collecting, by a processor of an electronic device, audio data;

updating, by the processor, a voice command that is set to execute a function through voice, wherein the updating is based on at least one of audio feature data extracted from the collected audio data, speech recognition data obtained by speech recognition of the collected audio data, or function execution data executed in relation to the collected audio data;

updating, by the processor, a weight of at least one of the audio feature data, the speech recognition data, and the function execution data; and

if the updated weight satisfies a specific condition, performing one of;

generating, by the processor, a candidate recognition model with the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and updating, by the processor, a weight of an existing candidate recognition model according to the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and changing, by the processor, an existing candidate recognition model into a recognition model corresponding to a voice command;

or

updating a weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data and removing at least one of a candidate recognition model and a recognition model corresponding to the updated weight.

9. The method of claim 8, further comprising:

registering a new voice command corresponding to the recognition model.

10. The method of claim 8, further comprising:

updating a weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data; and

removing at least one of a candidate recognition model and a recognition model corresponding to the weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data.

11. The method of claim 10, further comprising:

removing a registered voice command corresponding to the removing of the at least one of a candidate recognition model and a recognition model corresponding to the weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data.

12. The method of claim 8, further comprising:

outputting at least one of the audio feature data, the speech recognition data, the function execution information, and the voice command.

13. The method of claim 8, further comprising:

transmitting the collected audio data to a server device; and

receiving, from the server device, at least one of the audio feature data, the speech recognition data, and the function execution data.

14. The method of claim 13, further comprising:

receiving, from the server device, a voice command generated based on at least one of the audio feature data, the speech recognition data, and the function execution data.

15. A voice command providing method, comprising:

collecting, by a processor of an electronic device, audio data;

updating, by the processor, a voice command that is set to execute a function through voice, wherein the updating is based on at least one of audio feature data extracted from the collected audio data, speech recognition data obtained by speech recognition of the collected audio data, or function execution data executed in relation to the collected audio data; and

updating, by the processor, a weight of at least one of the audio feature data, the speech recognition data, and the function execution data,

wherein updating the weight comprises at least one of;

updating, by the processor, a weight of the audio feature data on the basis of a frequency of occurrence of the audio feature data and updating, by the processor, a weight of the speech recognition data on the basis of a frequency of occurrence of the speech recognition data and updating, by the processor, a weight of the function execution data on the basis of at least one of whether to execute a function of the function execution data and a function execution duration time of the function execution data;

or

updating a weight of at least one of a candidate recognition model with the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight and recognition model having no relation to the collected audio data and removing at least one of a candidate recognition model and a recognition model on the basis of the updated weight.

16. A chipset comprising:

a non-transitory computer-readable storage medium; and

at least one processor,

wherein, when executing instructions stored on the non-transitory computer-readable storage medium, the at least one processor;

collects audio data;

updates a voice command that is set to execute a function through voice, wherein the updating is based on at least one of audio feature data extracted from the collected audio data, speech recognition data obtained by speech recognition of the collected audio data, and function execution data executed in relation to the collected audio data;

updating a weight of at least one of the audio feature data, the speech recognition data, and the function execution data; and

if the updated weight satisfies a specific condition, performing one of;

generating a candidate recognition model with the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and updating a weight of an existing candidate recognition model according to the at least one of the audio feature data, the speech recognition data, and the function execution data associated with the updated weight, and changing an existing candidate recognition model into a recognition model corresponding to a voice command;

or

updating a weight of at least one of a candidate recognition model and recognition model having no relation to the collected audio data and removing at least one of a candidate recognition model and a recognition model corresponding to the updated weight.