Real-Time Speech Analysis Method and System

Patent metadata

Field	Value
Publication number	US-2020160880-A1
Application number	US-202016773335-A
Country	US
Kind code	A1
Filing date	Jan 27, 2020
Priority date	Jun 28, 2013
Publication date	May 21, 2020
Grant date	—

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 speed input; and processing the text to extract a context dialog prompt.

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

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

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

5 . 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.

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

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

8 . 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.

9 . 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.

10 . 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.

11 . The method of claim 10 , 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.

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.

13 . 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.

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

15 . 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.

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

17 . The system of claim 16 , wherein the error is identified by comparing the predicted speech meaning to the speech input.

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

• G09B19/06

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

• G10L15/00

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

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L25/48 Primary

  specially adapted for particular use · CPC title

• G09B19/04

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