Apparatus and method for recognizing voice and text

Patent metadata

Field	Value
Publication number	US-9613618-B2
Application number	US-201414324013-A
Country	US
Kind code	B2
Filing date	Jul 3, 2014
Priority date	Jul 4, 2013
Publication date	Apr 4, 2017
Grant date	Apr 4, 2017

Abstract

A method for recognizing a voice includes receiving, as an input, a voice involving multiple languages, recognizing a first voice of the voice by using a voice recognition algorithm matched to a preset primary language, identifying the preset primary language and a non-primary language different from the preset primary language, which are included in the multiple languages, determining a type of the non-primary language based on context information, recognizing a second voice of the voice in the non-primary language by applying a voice recognition algorithm, which is matched to the non-primary language of the determined type, to the second voice, and outputting a result of recognizing the voice which is based on a result of recognizing the first voice and a result of recognizing the second voice.

First claim

What is claimed is:

1. A method of recognizing a voice input signal involving multiple languages, the method comprising:
receiving the voice input signal which is input by a user;
recognizing the voice input signal by using a voice recognition algorithm for a primary language of the multiple languages;
identifying a segment of the voice input signal, which is in a non-primary language, in the voice input signal based on the recognition for the primary language;
determining a language of the segment of the voice input signal based on context information;
recognizing the segment of the voice input signal by using a voice recognition algorithm for the determined; and
outputting a recognition result of the voice input signal which is based on the recognition for the primary language and the recognition for the determined language.

2. The method as claimed in claim 1 , wherein the context information comprises at least one of:
whether a name of a country exists within the voice input signal;
information on a place where an apparatus for recognizing the voice input signal is located;
dialogue history information; and
an updated non-primary language database.

3. The method as claimed in claim 2 , wherein determining the language of the segment of the voice input signal based on the context information comprises:
determining that a language for the name of the country is the language of the segment of the voice input signal, if the language for the name of the country is not the primary language, when the name of the country exists within the voice input signal.

4. The method as claimed in claim 2 , wherein determining the language of the segment of the voice input signal based on the context information comprises:
determining that the language of the segment of the voice input signal is a language for at least one of characteristics of a country and a place where the apparatus for recognizing the voice input signal is located, based on measured Global Positioning System (GPS) coordinates.

5. The method as claimed in claim 2 , wherein determining the language of the segment of the voice input signal based on the context information comprises:
determining whether a dialogue history in which the language of the segment of the voice input signal and the name of the country co-exist has previously been stored; and
determining that the language of the segment of the voice input signal is a language for the name of the country, when there exists the dialogue history in which the language of the segment of the voice input signal and the name of the country co-exist.

6. The method as claimed in claim 2 , wherein determining the language of the segment of the voice input signal based on the context information comprises:
determining whether a history of recognizing the segment of the voice input signal exists in the non-primary language database; and
immediately recognizing, by the apparatus for recognizing the voice input signal, the language of the segment of the voice input signal based on a result of the recognition corresponding to the history of recognizing the segment of the voice input, when the history of recognizing the segment of the voice input signal exists in the non-primary language database.

7. The method as claimed in claim 6 , further comprising receiving the non-primary language database from an outside.

8. The method as claimed in claim 1 , wherein identifying the segment of the voice input signal, which is in the non-primary language, in the voice input signal based on the recognition for the primary language comprises:
segmenting the voice input signal in a unit of phoneme;
determining a similarity between at least one segmented phoneme and a word in the primary language by matching the at least one segmented phoneme with a database of phonemes in the primary language; and
identifying that the at least one segmented phoneme having the determined similarity less than a preset threshold belongs to the segment of the voice input signal.

9. The method as claimed in claim 1 , further comprising updating at least one of the context information and a voice recognition algorithm for the language of the segment of the voice input signal, by reflecting a result of recognizing the segment of the voice input signal in the at least one of the context information and the voice recognition algorithm for the language of the segment of the voice input signal.

10. The method as claimed in claim 9 , further comprising:
displaying the result of recognizing the segment of the voice input signal;
receiving, as an input, a user feedback indicating whether the result of recognizing the segment of the voice input signal is appropriate or inappropriate; and
updating a non-primary language database by reflecting the result of recognizing the segment of the voice input signal in the non-primary language database, when the user feedback indicates that the result of recognizing the segment of the voice input signal is appropriate.

11. The method as claimed in claim 10 , further comprising:
when the user feedback indicates that the result of recognizing the segment of the voice input signal is inappropriate, excluding the result of recognizing the segment of the voice input signal; and
re-recognizing the segment of the voice input signal, and outputting the re-recognized segment of the voice input signal.

12. An apparatus that recognizes a voice input signal involving multiple languages, the apparatus comprising:
a microphone configured to receive a voice input signal which is input by a user;
a storage unit configured to store a voice recognition algorithm for a primary language and a voice recognition algorithm for a non-primary language;
a controller configured to recognize the voice input signal by using the voice recognition algorithm for the primary language, identify a segment of the voice input signal, which is in the non- primary language, in the voice input signal based on the recognition for the primary language, determine a language of the segment of the voice input signal based on context information, and recognize the segment of the voice input signal by using a voice recognition algorithm for the determined language; and
a display unit configured to output a recognition result of the voice input signal which is based on the recognition for the primary language and the recognition for the determined language.

13. The apparatus as claimed in claim 12 , wherein the context information comprises at least one of:
whether a name of a country exists within the voice input signal;
information on a place where an apparatus for recognizing the voice input signal is located;
dialogue history information; and
an updated non-primary language database.

14. The apparatus as claimed in claim 13 , further comprising a Global Positioning System (GPS) module configured to measure GPS coordinates, where the apparatus configured to recognize the voice input signal is located, and output the measured GPS coordinates,
wherein the controller is configured to determine that a language for the name of the country is the language of the segment of the voice input signal, if the language for the name of the country is not the primary language, when the name of the country exists within the voice, or
wherein the controller is configured to determine that the language of the segment of the voice input signal is a language for at least one of characteristics of a country and a place where the apparatus for recognizing the voice input signal is located, based on the measured GPS coordinates.

15. The apparatus as

Assignees

• Samsung Electronics Co Ltd
• Samsung Electronics Co Ltd

Inventors

• Chakladar Subhojit

Classifications

• G06F40/263

  Language identification · CPC title

• G10L15/005 Primary

  Language recognition · CPC title

• G01C21/3664

  Details of the user input interface, e.g. buttons, knobs or sliders, including those provided on a touch screen; remote controllers; input using gestures · CPC title

• G10L2015/226

  using non-speech characteristics · CPC title

• G06F17/275

  Physics · mapped topic