VOICE RECOGNITION APPARATUS AND CONTROLLING METHOD THEREOF

• US 20170076724A1
• Filed: 07/13/2016
• Published: 03/16/2017
• Est. Priority Date: 09/14/2015
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd. (Samsung Group)
• Original Assignee: Samsung Electronics Co. Ltd. (Samsung Group)
• Inventors: SHIN, Sung-hwan, PARK, Kyung-mi, KWON, Nam-yeong
• Application Number:
  US15/208,846
• Publication Number:
  US 20170076724A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• 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 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/221 Announcement of recognition results
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04N 21/42203 sound input device, e.g. microphone
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/4828 for searching program descriptors retrieval of video data G06F16/739

Abstract

A voice recognition apparatus is provided. The voice recognition apparatus includes a communicator configured to communicate with an external voice recognition server; a memory configured to store a plurality of keywords and domain information corresponding to each of the plurality of keywords; a microphone configured to generate a voice signal corresponding to an uttered voice; and a controller configured to recognize a keyword included in the voice signal, determine a domain corresponding to the recognized keyword by using the domain information, and control the communicator to transmit information regarding the determined domain and the voice signal to the external voice recognition server.

Claims

1. A voice recognition apparatus, comprising:

a communicator configured to communicate with an external voice recognition server;

a memory configured to store a plurality of keywords and domain information corresponding to each of the plurality of keywords;

a microphone configured to generate a voice signal corresponding to an uttered voice; and

a controller configured to recognize a keyword included in the voice signal, determine a domain corresponding to the recognized keyword by using the domain information, and control the communicator to transmit information regarding the determined domain and the voice signal to the external voice recognition server.

2. The apparatus as claimed in claim 1, wherein in response to a keyword not being recognized from the voice signal, the controller does not process the voice signal.

3. The apparatus as claimed in claim 1, wherein the controller is configured to recognize a plurality of keywords included in the voice signal, determine a domain corresponding to each of the plurality of recognized keywords by using the domain information, and transmit information regarding the determined domain to the external voice recognition server.

4. The apparatus as claimed in claim 1, wherein the controller is configured to receive a result of voice recognition from the external voice recognition server, and transmit the received result of voice recognition to an external electronic apparatus.

5. The apparatus as claimed in claim 1, further comprising;

a display configured to, in response to receiving a result of voice recognition from the external voice recognition server, display the received result of voice recognition.

6. The apparatus as claimed in claim 5, wherein a plurality of keywords stored in the memory include a trigger keyword for initiating voice recognition,

wherein the controller is configured to control the display to display a UI screen for inducing a subsequent utterance if only the trigger keyword is included in the voice signal, in response to an input of the subsequent utterance, determine a domain corresponding to the trigger keyword included in a voice signal corresponding to the subsequent utterance by using the domain information, and transmit information regarding the determined domain and the voice signal corresponding to the subsequent utterance to the external voice recognition server.

7. The apparatus as claimed in claim 6, wherein the UI screen for inducing a subsequent utterance includes a screen for inducing an utterance regarding a topic corresponding to the determined domain.

8. The apparatus as claimed in claim 5, wherein the controller is configured to control the display to display a UI screen including a plurality of keywords stored in the memory and domain information corresponding to each of the plurality of keywords.

9. The apparatus as claimed in claim 1, wherein, the controller is configured to, in response to receiving a user manipulation command to register a new keyword and domain information corresponding to the new keyword, store the new keyword and the domain information corresponding to the new keyword in the memory.

10. The apparatus as claimed in claim 1, wherein the controller is configured to, in response to receiving a user manipulation command to edit domain information corresponding to at least one of a plurality of keywords stored in the memory, update the domain information corresponding to the at least one of the plurality of keywords stored in the memory based on the received user manipulation command.

11. The apparatus as claimed in claim 10, wherein the controller is configured to transmit the plurality of keywords stored in the memory and the domain information corresponding to each of the plurality of keywords to an external apparatus, and control the communicator to receive the user manipulation command from the external apparatus.

12. A control method of the voice recognition apparatus storing a plurality of keywords and domain information corresponding to each of the plurality of keywords, comprising:

generating a voice signal corresponding to an uttered voice;

recognizing a keyword included in the voice signal; and

determining a domain corresponding to the recognized keyword by using the domain information, and transmitting information regarding the determined domain and the voice signal to an external voice recognition server.

13. The method as claimed in claim 12, wherein the recognizing the keyword comprises, in response to a keyword not being recognized from the voice signal, not processing the voice signal.

14. The method as claimed in claim 12, wherein the recognizing the keyword comprises recognizing a plurality of keywords included in the voice signal, and the transmitting comprises determining a domain corresponding to each of the plurality of recognized keywords by using the domain information, and transmitting information regarding the determined domain to the external voice recognition server.

15. The method as claimed in claim 12, further comprising receiving a result of voice recognition from the external voice recognition server, and transmitting the received result of voice recognition to an external electronic apparatus.

16. The method as claimed in claim 12, further comprising, in response to receiving a result of voice recognition from the external voice recognition server, displaying the received result of voice recognition.

17. The method as claimed in claim 12, further comprising displaying a UI screen including the plurality of stored keywords and the domain information corresponding to each of the plurality of keywords.

18. The method as claimed in claim 12, further comprising:

receiving a user manipulation command for editing domain information corresponding to the at least one of the plurality of stored keywords; and

updating domain information corresponding to at least one of the plurality of stored keywords based on the received user manipulation command.

19. The method as claimed in claim 18, wherein the receiving the user manipulation command comprises transmitting the plurality of stored keywords and the domain information corresponding to each of the plurality of keywords to an external apparatus, and receiving the user manipulation command from the external apparatus.

20. A non-transitory recording medium for storing a program for a control method of the voice recognition apparatus storing a plurality of keywords and domain information corresponding to each of the plurality of keywords, the method comprising:

generating a voice signal corresponding to an uttered voice;

recognizing a keyword included in the voice signal; and

determining a domain corresponding to the recognized keyword by using the domain information, and transmitting information regarding the determined domain and the voice signal to an external voice recognition server.