Method for correcting voice recognition error and broadcast receiving apparatus applying the same

• US 9,245,521 B2
• Filed: 06/21/2013
• Issued: 01/26/2016
• Est. Priority Date: 07/12/2012
• Status: Expired due to Fees

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Park, Sung-woo, Kim, Jae-cheol, Jung, Jae-wook
• Primary Examiner(s): AZAD, ABUL K
• Application Number:
  US13/923,813
• Publication Number:
  US 20140019127A1
• Time in Patent Office: 949 Days
• Field of Search: 704/235, 704/275, 704/270
• US Class Current: 1/1
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/221 Announcement of recognition results

Abstract

A method for correcting a voice recognition error and a broadcast receiving apparatus applying the same are provided. The method for correcting the voice recognition error includes, receiving a user'"'"'s spoken command, recognizing the user'"'"'s spoken command and determining text corresponding to the user'"'"'s spoken command, if a user command to correct the determined text is input, displaying a text correction user interface in which a morpheme of the determined text and an indicator are associated with each other, and correcting the morpheme of the determined text by selecting the associated indicator of the text correction UI. Accordingly, the broadcast receiving apparatus exactly corrects the misrecognized word with a word desired by the user.

Claims

1. A method for correcting a voice recognition error of a broadcast receiving apparatus, the method comprising:

receiving a user'"'"'s spoken command;

recognizing the user'"'"'s spoken command; and

determining text corresponding to the user'"'"'s spoken command;

if a user command to correct the determined text is input, displaying a text correction user interface (UI) which comprises a morpheme of the determined text and an indicator corresponding to the morpheme of the determined text; and

correcting the morpheme corresponding to the indicator selected by a user voice comprising the indicator.

2. The method as claimed in claim 1, wherein the morpheme is an initial morpheme and the correcting comprises:

if the initial morpheme is selected using the associated indicator, displaying a candidate morpheme corresponding to the initial morpheme; and

if the candidate morpheme is selected, correcting the initial morpheme by replacing the initial morpheme with the selected candidate morpheme.

3. The method as claimed in claim 2, wherein the displaying the candidate morpheme comprises displaying a second indicator corresponding to the candidate morpheme on one side of the candidate morpheme.

4. The method as claimed in claim 3, wherein the correcting the target morpheme comprises, if the second indicator corresponding to the candidate morpheme is selected, correcting the initial morpheme to be replaced by replacing the initial morpheme with the candidate morpheme corresponding to the selected indicator.

5. The method as claimed in claim 1, wherein the indicator comprises one from among a number and a character.

6. The method as claimed in claim 1, wherein the determining comprises:

converting the user'"'"'s spoken command from an analogue signal format into a digital signal format;

transmitting the user'"'"'s spoken command in the digital signal format to an external server; and

receiving text information corresponding to the user'"'"'s spoken command in the digital signal format from the server.

7. The method as claimed in claim 6, further comprising transmitting a result of the correcting to the server to update a language model and a sound model stored in the server.

8. A broadcast receiving apparatus comprising:

a voice input which receives a user'"'"'s spoken command; and

a controller which, if a user'"'"'s spoken command is input through the voice input, recognizes the user'"'"'s spoken command and determines text corresponding to the user'"'"'s spoken command, if a second user command to correct the determined text is input, displays a text correction user interface (UI) which comprises a morpheme of the determined text and an indicator corresponding to the morpheme of the determined text, and controls a display to correct the morpheme corresponding to the indicator selected by a user voice comprising the indicator.

9. The broadcast receiving apparatus as claimed in claim 8, wherein the morpheme is an initial morpheme, if the initial morpheme is selected using the associated indicator, the controller displays a candidate morpheme corresponding to the initial morpheme, and, if the candidate morpheme is selected, the controller controls the display to correct the initial morpheme by replacing the initial morpheme with the selected candidate morpheme.

10. The broadcast receiving apparatus as claimed in claim 9, wherein the controller controls the display to display a second indicator corresponding to the candidate morpheme on one side of the candidate morpheme.

11. The broadcast receiving apparatus as claimed in claim 10, wherein, if the second indicator corresponding to the candidate morpheme is selected, the controller controls the display to correct the initial morpheme to be replaced by replacing the initial morpheme the candidate morpheme corresponding to the selected indicator.

12. The broadcast receiving apparatus as claimed in claim 8, wherein the indicator comprises one from among a number and a character.

13. The broadcast receiving apparatus as claimed in claim 8, further comprising a communicator which communicates with an external server,

wherein, if a user'"'"'s spoken command is input through the voice input, the controller converts the user'"'"'s spoken command from an analogue signal format into a digital signal format, transmits the user'"'"'s spoken command in the digital signal format to the external server through the communicator, receives text information corresponding to the user'"'"'s spoken command in the digital signal format from the server, and determines the text information.

14. The broadcast receiving apparatus as claimed in claim 13, wherein the controller controls the communicator to transmit a result of the correcting to the server to update a language model and a sound model stored in the server.

15. A method for correcting a voice recognition error of a broadcast receiving apparatus, the method comprising:

recognizing a user'"'"'s spoken command;

determining text corresponding to the user'"'"'s spoken command;

displaying an indicator which comprises a morpheme of the determined text; and

correcting the morpheme corresponding to the indicator selected by a user voice comprising the indicator.

16. The method as claimed in claim 15, wherein the correcting comprises:

displaying a candidate morpheme corresponding to the morpheme of the determined text in response to receiving the user voice corresponding to the indicator; and

selecting the candidate morpheme and correcting the morpheme of the determined text by replacing the morpheme of the determined text with the selected candidate morpheme.

17. The method as claimed in claim 16, further comprising transmitting a result of the correcting to a server to update a language model and a sound model stored in the server.