Real-time speech analysis method and system using speech recognition and comparison with standard pronunciation

Patent metadata

Field	Value
Publication number	US-11062726-B2
Application number	US-202016773335-A
Country	US
Kind code	B2
Filing date	Jan 27, 2020
Priority date	Jun 28, 2013
Publication date	Jul 13, 2021
Grant date	Jul 13, 2021

Abstract

A method of providing real-time speech analysis to a user includes capturing a speech input, performing a real-time recognition of the speech input including converting the speech input to a text, analyzing the recognized speech input to identify an error in a voice of the user, the analyzing including comparing a voice of a correct text generated by an automated speech generation system with the captured speed input, and processing the text to extract a context dialog prompt.

First claim

What is claimed is:

1. A method of providing real-time speech analysis to a user, the method comprising:
capturing a speech input;
performing a real-time recognition of the speech input including converting the speech input to a text;
analyzing the recognized speech input to identify an error in a voice of the user, the analyzing including comparing a voice of a correct text generated by an automated speech generation system with the captured speech input; and
processing the text to extract a context dialog prompt,
wherein the comparing the voice of the correct text with the captured speech input includes comparing a standard pronunciation of the correct text with a pronunciation of the user in the captured speech input to identify the error in the speech.

2. The method of claim 1 , further comprising:
extracting a user generated error; and
summarizing a common error pattern with a machine learning algorithm,
wherein at least one of the error generated by the user and the common error pattern is stored in a user profile.

3. The method of claim 2 , wherein the user profile comprises at least one of a user nationality, a user accent, and a user history, the user history including an analyzed user speech, a prior response to the identified error, a prior user feedback, and at least one of fault tolerance preferences of the user.

4. The method of claim 1 , wherein the speech input comprises a speech from the user and at least one speaker other than the user.

5. The method of claim 1 , wherein the error comprises at least one of a pronunciation error and a syntax error.

6. The method of claim 1 , wherein the analyzing comprises a semantic analysis.

7. The method of claim 1 , wherein the performing real-time recognition comprises using a voice prompt from at least one speaker other than the user.

8. The method of claim 1 , wherein the context dialog prompt identifies the error.

9. The method of claim 1 , further comprising providing the user with suggested error corrections in a real time.

10. The method of claim 1 , further comprising creating a customized user learning session,
wherein the learning session comprises an interactive learning session, and
wherein the learning session is based on a common error mode.

11. The method of claim 1 , further comprising outputting at least one of the identified error, visual corrections, audible corrections, and suggested synonyms to the user.

12. A system for providing a real-time speech analysis, the system comprising:
a capture module for capturing a speech input;
an automatic speech recognition module for performing real-time recognition of the speech input including converting the speech to a text;
an analysis module for analyzing the recognized speech input to identify an error including comparing the speech of a correct text generated by an automated speech generation system with the captured speech input; and
a processor to process the text to extract a context dialog prompt,
wherein the comparing the voice of the correct text with the captured speech input includes comparing a standard pronunciation of the correct text with a pronunciation of the user in the captured speech input to identify the error in the speech.

13. The system of claim 12 , wherein the analysis module generates a predicted speech meaning based on the speech input.

14. The system of claim 13 , wherein the error is identified by comparing the predicted speech meaning to the speech input.

15. The system of claim 12 , further comprising a lesson planner module for scheduling at least one of a predefined course and an automatically created course.

16. The system of claim 12 , further comprising an error summary module for determining one or more error patterns.

17. The system of claim 12 , further comprising a user profile module that stores at least one of an error summary and a user error mode.

18. The system of claim 12 , wherein the capturing of the speech input comprises continuously monitoring a voice input.

19. The system of claim 12 , further comprising an interactive user interface module that uses feedback information of the user to analyze the error and to suggest an error correction.

20. The system of claim 12 , wherein the capturing of the speech input comprises continuously receiving a voice input.

Assignees

• IBM

Inventors

• Caskey Sasha P
• Ni Jian
• Sakrajda Andrzej
• Wan Hui
• Wu Cheng

Classifications

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G09B19/06

  Foreign languages (with audible presentation of material to be studied G09B5/04) · CPC title

• G10L25/48 Primary

  specially adapted for particular use · CPC title