Apparatus and system for speech intent recognition

• US 9,767,710 B2
• Filed: 10/15/2010
• Issued: 09/19/2017
• Est. Priority Date: 12/16/2009
• Status: Active Grant

• Current Assignee: Postech Academy-Industry Foundation
• Original Assignee: Postech Academy-Industry Foundation
• Inventors: Lee, Sung Jin, Lee, Cheong Jae, Lee, Gary Geunbae
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US13/515,811
• Publication Number:
  US 20120290300A1
• Time in Patent Office: 2,531 Days
• Field of Search: 704251
• CPC Class Codes: G09B 19/04 Speaking with audible presentation of the material to be studied G09B5/04
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04

Abstract

The apparatus for foreign language study includes: a voice recognition device configured to recognize a speech entered by a user and convert the speech into a speech text; a speech intent recognition device configured to extract a user speech intent for the speech text using skill level information of the user and dialog context information; and a feedback processing device configured to extract a different expression depending on the user speech intent and a speech situation of the user. According to the present invention, the intent of a learner'"'"'s speech may be determined even though the learner'"'"'s skill is low, and customized expressions for various situations may be provided to the learner.

Claims

1. An apparatus for speech intent recognition, comprising:

a speech recognition device configured to recognize a speech entered by a user and convert the speech into a speech text;

a speech intent recognition device configured to extract a user speech intent for the speech text using skill level information of the user and dialogue context information; and

a feedback processing device configured to extract an expression depending on the user speech intent and a speech situation of the user,

wherein the speech intent recognition device selects a speech-based model among a plurality of speech-based models based on the skill level information of the user, estimates a speech intent for the speech text using the selected speech-based model, estimates a speech intent based on the dialogue context information using a dialogue context-based model, and combines the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model to extract the user speech intent,

wherein the apparatus for speech intent recognition outputs the expression extracted by the feedback processing device as a voice through a speaker or as a text form on a display screen,

wherein the plurality of speech-based models are separately modeled for respective learner levels and classified into the respective learner levels based on philological information,

wherein the dialogue context-based model is based on a list of speeches previous to the speech entered by the user, and

wherein the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model are simultaneously estimated.

2. The apparatus of claim 1, wherein the speech intent recognition device extracts the user speech intent using the plurality of speech-based models which are separately generated for skill levels of the user and the dialogue context-based model which is generated by considering the dialogue context information.

3. The apparatus of claim 1, further comprising a dialogue managing module configured to generate a response to the speech text according to the user speech intent and the dialogue context information.

4. The apparatus of claim 1, wherein, when a speech of the user is not inputted within a preset time or a help request is made from the user, the feedback processing device extracts a recommended expression from a database and provides the recommended expression to the user.

5. The apparatus of claim 1, wherein, when the user'"'"'s speech is right, the feedback processing device extracts an alternative expression having the same meaning as or a similar meaning to the user'"'"'s speech from a database, and provides the alternative expression to the user.

6. The apparatus of claim 1, further comprising:

a natural language generating device configured to convert the expression extracted by the feedback processing device into a natural language speech; and

a voice synthesizing device configured to synthesize the natural language speech converted by the natural language generating device into the voice.

7. The apparatus of claim 1, wherein, when the user'"'"'s speech is not right, the feedback processing device selects a sentence which best coincides with the user speech intent from a database, extracts the selected sentence as a right expression, and provides the right expression to the user.

8. An apparatus for speech intent recognition, comprising:

a speech recognition device configured to recognize a speech entered by a user and convert the speech into a speech text;

a speech intent recognition device configured to extract a user speech intent for the speech text; and

a feedback processing device configured to extract a recommended expression, a right expression, or an alternative expression according to the user speech intent and a speech situation of the user, and provides the extracted expression to the user,

wherein the speech intent recognition device selects a speech-based model among a plurality of speech-based models based on skill level information of the user, estimates a speech intent for the speech text using the selected speech-based model, estimates a speech intent based on dialogue context information using a dialogue context-based model, and combines the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model to extract the user speech intent,

wherein the apparatus for speech intent recognition outputs the expression extracted by the feedback processing device as a voice through a speaker or as a text form on a display screen,

wherein the plurality of speech-based models are separately modeled for respective learner levels and classified into the respective learner levels based on philological information,

wherein the dialogue context-based model is based on a list of speeches previous to the speech entered by the user, and

wherein the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model are simultaneously estimated.

9. The apparatus of claim 8, wherein the feedback processing device extracts the recommended expression from a database when a speech of the user is not inputted within a preset time or a help request is made from the user, selects a sentence which best coincides with the user speech intent from a database when the user'"'"'s speech is not right, and extracts the alternative expression from a database when the user'"'"'s speech is right.

10. A dialogue system comprising:

a speech recognition device configured to recognize a speech entered by a user and convert the speech into a speech text; and

a speech intent recognition device configured to extract a user speech intent for the speech text using a plurality of speech-based models which are separately generated for skill levels of the user and a dialogue context model generated by considering dialogue context information,

wherein the speech intent recognition device selects one of the plurality of speech-based models based on the skill level information of the user, estimates a speech intent for the speech text using the selected speech-based model, estimates a speech intent based on the dialogue context information using the dialogue context-based model, and combines the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model to extract the user speech intent,

wherein the speech intent recognition device extracts an expression depending on the user speech intent and a speech situation of the user, and outputs the extracted expression as a voice through a speaker or as a text form on a display screen,

wherein the plurality of speech-based models are separately modeled for respective learner levels and classified into the respective learner levels based on philological information,

wherein the dialogue context-based model is based on a list of speeches previous to the speech entered by the user, and

wherein the speech intent based on the speech-based model and the speech intent based on the dialogue context-based model are simultaneously estimated.