Grammar correcting method and apparatus

Patent metadata

Field	Value
Publication number	US-2016196257-A1
Application number	US-201514749747-A
Country	US
Kind code	A1
Filing date	Jun 25, 2015
Priority date	Jan 2, 2015
Publication date	Jul 7, 2016
Grant date	—

Abstract

A grammar correcting method is provided, the method including receiving a sentence generated based on speech recognition, receiving information associated with a speech recognition result of the sentence and correcting grammar in the sentence based on the information associated with the speech recognition results of the sentence.

First claim

What is claimed is:

1 . A grammar correcting method, comprising:
receiving a sentence generated based on speech recognition; receiving information associated with a speech recognition result of the sentence; and correcting grammar in the sentence based on the information associated with the speech recognition result of the sentence.

2 . The method of claim 1 , wherein the information associated with the speech recognition result of the sentence comprises recognition reliabilities of words in the sentence.

3 . The method of claim 1 , wherein the information associated with the speech recognition result of the sentence is determined based on at least one of a recognition reliability associated with a pronunciation of the sentence and a recognition reliability associated with an intention of the sentence.

4 . The method of claim 1 , wherein the information associated with the speech recognition result of the sentence is determined based on at least one of a language model and an acoustic model for generating the sentence.

5 . The method of claim 1 , wherein the correcting the grammar in the sentence comprises:
detecting a plurality of candidate words associated with a grammatical error among words comprised in the sentence by verifying grammar in the sentence; selecting at least one candidate word among the plurality of candidate words based on the information associated with the speech recognition result of the sentence; and correcting the at least one selected candidate word.

6 . The method of claim 5 , wherein the plurality of candidate words are grammatically associated with each other.

7 . The method of claim 5 , wherein the selecting the at least one candidate word comprises selecting a candidate word having a lowest degree of recognition reliability among the plurality of candidate words.

8 . The method of claim 1 , further comprising:
generating the sentence by recognizing a speech based on a language model and an acoustic model.

9 . A computer program combined with hardware and stored in a non-transitory computer-readable storage medium to cause a computer to perform the method of claim 1 .

10 . A grammar correcting apparatus, comprising:
a verifier configured to verify grammar in a sentence corresponding to a speech recognition result; and a corrector configured to correct the grammar in the sentence based on recognition reliabilities of words in the sentence.

11 . The apparatus of claim 10 , wherein the verifier is further configured to detect a plurality of candidate words associated with a grammatical error among words comprised in the sentence.

12 . The apparatus of claim 11 , wherein the plurality of candidate words are grammatically associated with each other.

13 . The apparatus of claim 10 , wherein the corrector is further configured to select at least one candidate word among a plurality of candidate words associated with a grammatical error based on the recognition reliabilities of the words in the sentence, and correct the at least one selected candidate word.

14 . The apparatus of claim 13 , wherein the corrector is further configured to select a candidate word having a lowest degree of recognition reliability among the plurality of candidate words.

15 . The apparatus of claim 10 , wherein the recognition reliabilities of the words in the sentence are determined based on at least one of a recognition reliability associated with a pronunciation of the sentence and a recognition reliability associated with an intention of the sentence.

16 . The apparatus of claim 10 , wherein the recognition reliabilities of the words in the sentence are determined based on at least one of a language model and an acoustic model for generating the sentence based on speech recognition.

17 . The apparatus of claim 10 , further comprising:
a speech recognizer configured to recognize a speech based on a language model and an acoustic model.

18 . A grammar correcting apparatus, comprising:
a first receiver configured to receive a sentence generated based on speech recognition; a second receiver configured to receive information associated with a speech recognition result; and a grammar corrector configured to correct grammar in the sentence based on the information associated with the speech recognition result.

19 . The apparatus of claim 18 , wherein the grammar corrector comprises:
a verifier configured to detect a plurality of candidate words associated with a grammatical error included in the sentence by verifying grammar in the sentence; a selector configured to select at least one candidate word among the plurality of candidate words based on the information associated with the speech recognition result; and a corrector configured to correct the at least one candidate word selected by the selector.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Choi Heeyoul

Classifications

• G10L15/19 Primary

  Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules · CPC title

• G06F40/253 Primary

  Grammatical analysis; Style critique · CPC title

• G10L15/26

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

• G10L15/005

  Language recognition · CPC title

• G06F17/274 Primary

  Physics · mapped topic