VOICE RECOGNITION APPARATUS, DRIVING METHOD THEREOF, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM

• US 20170069317A1
• Filed: 06/29/2016
• Published: 03/09/2017
• Est. Priority Date: 09/04/2015
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: KWON, Nam-yeong
• Application Number:
  US15/197,015
• Publication Number:
  US 20170069317A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A voice recognition apparatus includes a voice recognition processor configured to determine whether or not a voice command included in log data related to operation execution of an apparatus is a normal recognition utterance intentionally uttered by a user by analyzing the log data, and build a DB with respect to a recognition result of the voice command determined as the normal recognition utterance as a determination result.

Claims

1. A voice recognition apparatus comprising:

a voice recognition microprocessor configured to analyze log data related to operation execution of the voice recognition apparatus, determine whether or not a voice command included in the log data is a normal recognition utterance, which has been intentionally uttered by a user to operate the voice recognition apparatus, based on a result of an analysis, and build a recognition result of the voice command, which is determined as the normal recognition utterance, as a determination result in a database (DB).

2. The voice recognition apparatus as claimed in claim 1, wherein the voice recognition microprocessor is configured to confirm whether the voice command is included in the log data, and determine whether the voice command is the normal recognition utterance by confirming an operation state of the voice recognition apparatus subsequent to the voice command being confirmed based on the log data.

3. The voice recognition apparatus as claimed in claim 2, wherein the voice recognition microprocessor is configured to determine the voice command as the normal recognition utterance, in response to another voice command uttered subsequent to the voice command being confirmed by the operation state.

4. The voice recognition apparatus as claimed in claim 2, wherein the voice recognition microprocessor is configured to determine the voice command as a misrecognition utterance, which has been unintentionally uttered by the user, in response to an absence of a user utterance subsequent to the voice command within a certain time or a power to the voice recognition apparatus being turned off as the operation state.

5. The voice recognition apparatus as claimed in claim 2, wherein the voice recognition microprocessor is configured to temporarily store the recognition result determined as the normal recognition utterance, and a recognition result determined as a misrecognition utterance, which has been unintentionally uttered by the user, and verify whether or not a recognition rate is improved by the temporarily stored recognition results by checking whether or not preset audio experiment data is recognized as the temporarily stored recognition results.

6. The voice recognition apparatus as claimed in claim 2, wherein the voice recognition microprocessor is configured to temporarily store the recognition result determined, as the normal recognition utterance, and a recognition result determined, as a misrecognition utterance, which has been unintentionally uttered by the user, and verify whether or not a recognition rate is improved by the temporarily stored recognition results by determining whether or not the received voice command is recognized as the temporarily stored recognition results.

7. The voice recognition apparatus as claimed in claim 5, wherein the voice recognition microprocessor is configured to build the recognition result of which the recognition rate is improved as a verification result in the DB.

8. The voice recognition apparatus as claimed in claim 1, further comprising:

a communication interface configured to transmit the log data to a server-based voice recognition apparatus to build the recognition result in the DB of the server-based voice recognition apparatus.

9. The voice recognition apparatus as claimed in claim 8, wherein the communication interface is configured to transmit the log data as a text-based recognition result acquired by analyzing audio data of the voice command.

10. A method of driving a voice recognition apparatus, the method comprising:

analyzing log data related to operation execution of the voice recognition apparatus;

determining whether or not a voice command included in the log data is a normal recognition utterance, which has been intentionally uttered by a user to operate the the voice recognition apparatus, based on a result of the analyzing; and

building a recognition result of the voice command determined, as the normal recognition utterance, as a determination result in a database (DB).

11. The method as claimed in claim 10, wherein the determining includes:

confirming the normal recognition utterance by confirming whether the voice command is included in the log data, and by confirming an operation state of the voice recognition apparatus subsequent to the voice command being confirmed based on the log data.

12. The method as claimed in claim 11, wherein the determining includes:

determining the voice command as the normal recognition utterance, in response to another voice command uttered subsequent to the voice command being confirmed by the operation state.

13. The method as claimed in claim 11, wherein the determining includes:

determining the voice command as a misrecognition utterance, which has been unintentionally uttered by the user, in response to an absence of a user utterance subsequent to the voice command within a certain time or a power of the voice recognition apparatus being turned off as the operation state.

14. The method as claimed in claim 11, further comprising:

storing preset audio experiment data;

temporarily storing the recognition result determined as the normal recognition utterance and a recognition result determined as a misrecognition utterance unintentionally uttered by the user; and

verifying whether or not a recognition rate is improved by the temporarily stored recognition results by checking whether or not the preset audio experiment data is recognized as the temporarily stored recognition results.

15. The method as claimed in claim 11, further comprising:

temporarily storing the recognition result determined as the normal recognition utterance and a recognition result determined as a misrecognition utterance unintentionally uttered by the user; and

verifying whether or not a recognition rate is improved by the temporarily stored recognition results by determining whether or not the received voice command is recognized as the temporarily stored recognition results.

16. The method as claimed in claim 15, wherein the building the DB includes:

building the DB with respect to the recognition result of which the recognition rate is improved as a verification result.

17. The method as claimed in claim 10, further comprising:

transmitting the log data to a server-based voice recognition apparatus to build the DB with respect to the recognition result in the server-based voice recognition apparatus.

18. The method as claimed in claim 17, wherein the transmitting includes:

transmitting the log data as a text-based recognition result acquired by analyzing audio data of the voice command.

19. A non-transitory computer-readable recording medium including a program for executing a method of driving a voice recognition apparatus, the method comprising:

analyzing log data related to operation execution of the voice recognition apparatus;

determining whether or not a voice command included in the log data is a normal recognition utterance, which has been intentionally uttered by a user to operate the the voice recognition apparatus, based on a result of the analyzing; and

building a recognition result of the voice command determined as the normal recognition utterance as a determination result in a database (DB).