METHOD AND APPARATUS OF TRANSLATING LANGUAGE USING VOICE RECOGNITION

• US 20100036653A1
• Filed: 03/30/2009
• Published: 02/11/2010
• Est. Priority Date: 08/11/2008
• Status: Active Grant

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: KIM, Yu Jin, SHIN, Won Ho
• Granted Patent: US 8,407,039 B2
• Time in Patent Office: Days
• US Class Current: 704/3
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The present invention relates to a method and apparatus of translating a language using voice recognition. The present invention provides a method of translating a language using voice recognition, comprising: receiving a voice input comprising a first language; acquiring at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input; providing a user interface for selecting at least one of the acquired at least one recognition candidate; and outputting a second language corresponding to the selected at least one recognition candidate, wherein the type of the user interface is determined according to the number of the acquired at least one recognition candidate, and an apparatus of translating a language using voice recognition for implementing the above method.

Claims

1. A method of translating a language using voice recognition, comprising:

receiving a voice input comprising a first language;

acquiring at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input;

providing a user interface for selecting at least one of the acquired at least one recognition candidate; and

outputting a second language corresponding to the selected at least one recognition candidate,

wherein the type of the user interface is determined according to the number of the acquired at least one recognition candidate2.

2. The method of claim 1, wherein the acquisition of at least one recognition candidate and the outputting of a second language are performed with reference to a database in which the first language and the second language are matched with each other for each of a plurality of categories.

3. The method of claim 2, wherein, in the provision of a user interface, if the number of the at least one recognition candidate is more than a reference value, a user interface for selecting the categories is provided.

4. The method of claim 1, wherein, in the provision of a user interface, if the number of the at least one recognition candidate is more than a reference value, a user interface for selecting an expression included in the voice input is provided.

5. The method of claim 1, wherein the user interface is provided in graphics or audio.

8. The method of claim 1, wherein the outputting of the at least one category comprises outputting the number of the at least one recognition candidate respectively contained in the at least one category.

6. A method of translating a language using voice recognition, comprising:

receiving a voice input comprising a first language;

outputting at least one category each including at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input;

selecting one of the at least one category;

outputting the at least one recognition candidate contained in the selected category;

selecting any one of the outputted at least one recognition candidate; and

outputting translation data corresponding to the selected recognition candidate and comprising a second language.

7. The method of claim 6, wherein the at least one category is classified by them or language.

9. A method of translating a language using voice recognition, comprising:

receiving a voice input comprising a first language;

acquiring at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input;

providing a user interface for receiving one of expressions related to the voice input;

receiving one of expressions related to the voice input through the user interface;

outputting at least one recognition candidate related to the received expression;

selecting any one of the at least one recognition candidate related to the received expression; and

outputting translation data corresponding to the selected recognition candidate and comprising a second language.

10. The method of claim 9, wherein the one of the expressions is contained in the voice input.

11. The method of claim 10, wherein the user interface is for selecting the one of the expressions.

12. The method of claim 9, wherein the one of the expressions is a keyword related to the voice input.

13. An apparatus of translating a language using voice recognition, comprising:

a voice input unit for receiving a voice input comprising a first language;

a voice recognition unit for acquiring at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input;

a memory storing a plurality of user interfaces for selecting at least one of the acquired at least one recognition candidate and a database in which the first and second languages are matched with each other for each of a plurality of categories; and

a controller for providing any one of the plurality of user interfaces according to the number of the acquired at least one recognition candidate, receiving a selection signal for at least one of the acquired at least one recognition candidate through the provided user interface, and outputting translation data comprising the second language corresponding to the selected at least one recognition candidate with reference to the database.

14. The apparatus of claim 13, wherein, if the number of the at least one recognition candidate is more than a reference value, the controller provides a user interface for selecting a category.

15. The apparatus of claim 13, wherein, if the number of the acquired recognition candidate is more than a reference value, the controller provides an interface for selecting one of expressions contained in the voice input.

16. The apparatus of claim 13, wherein the user interface is provided in at least one of graphics and audio.

17. The apparatus of claim 13, wherein the controller outputs the second language in the form of at least one of visual information and voice information.

18. The apparatus of claim 17, further comprising a voice synthesis unit for synthesizing the second language into voice, wherein, if the second language is outputted in the form of voice information, the controller synthesizes the second language into voice and outputs the same by controlling the voice synthesis unit.

19. A method of translating a language using voice recognition in an electronic device providing a voice recognition function and having a display, the method comprising:

receiving a voice input comprising a first language and containing a plurality of words;

acquiring a recognition candidate corresponding to the voice input by performing voice recognition on the voice input in units of words;

displaying the recognition candidate on the display in such a manner as to distinguish a word having a confidence below a reference value among the plurality of words from the other words;

changing the word having a confidence below a reference value into a new word; and

replacing the word having a confidence below a reference value with a second language corresponding to the new word and displaying the second language corresponding to the recognition candidate on the display.

20. The method of claim 19, wherein, in the displaying of the recognition candidate, the word having a confidence below the reference value is displayed in a different shape or color from the other words.

21. A method of translating a language using voice recognition in an electronic device providing a voice recognition function and having a display, the method comprising:

receiving a voice input comprising a first language and containing a plurality of words; and

displaying translation data comprising a second language corresponding to the voice input by performing voice recognition on the voice input in units of words,

wherein, in the displaying translation data, a word comprising a second language corresponding to a word having a confidence below a reference value among the plurality of words is displayed distinguishably from the other words comprising the translation data.

22. The method of claim 21, further comprising:

if the word displayed distinguishably from the other words is selected, providing a user interface for changing the selected word.

23. A method of translating a language using voice recognition in an electronic device providing a voice recognition function and having a display, the method comprising:

(a) receiving a voice input comprising a first language;

(b) acquiring translation data comprising a second language corresponding to the voice input by performing voice recognition on the voice input;

(c) storing the translation data in a translation file upon receipt of a first preset command signal; and

(d) repetitively performing steps (a) to (c) until a second preset command signal is received,

wherein the translation data acquired each time steps (a) to (c) are repetitively performed is added and stored in the translation file.