Recognition text error detection method and device
A text and error detection technology, applied in instruments, calculations, electrical digital data processing, etc., can solve the problems of low error detection accuracy and single error detection basis, and achieve the effect of improving error detection accuracy
Active Publication Date: 2019-09-13
新疆声谷融创数字产业发展有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since the error detection is based on the recognition confidence of each word in the recognition process, the error detection basis is relatively single, so the error detection accuracy is low
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] The specific implementation manners of the embodiments of the present invention will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the embodiments of the present invention, but are not intended to limit the scope of the embodiments of the present invention.
[0038] Speech translation refers to the process of automatically translating a speech signal in a source language into a speech signal in a target language. Speech translation generally includes three main components: speech recognition, machine translation and speech synthesis. Specifically, when a speech signal in the source language is given, the recognition text of the source language is first obtained through the speech recognition system, and then the recognition text is translated into the target language text through the machine translation system, and finally the target language text is synthesized into Speech signal in...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
An embodiment of the invention provides a recognition text error detection method and device and belongs to the technical field of language processing. The method includes: acquiring recognition confidence coefficient, translation confidence coefficient and context confidence coefficient of each segmented word in a recognition text; integrating the confidence coefficient, the translation confidence coefficient and the context confidence coefficient of each segmented word in the recognition text to acquire a comprehensive confidence coefficient score of each segmented word in the recognition text, and taking the segmented words with the comprehensive confidence coefficient score smaller than a preset threshold value as wrong words in the recognition text. Credibility of each segmented wordserving as a recognition result can be determined reversely on the basis of the translation confidence coefficient, and credibility of each segmented word serving as a recognition result in a contextbefore or after translation can be determined on the basis of the context confidence coefficient, so that when the translation confidence coefficient, the context confidence coefficient and the recognition confidence coefficient are combined to detect errors of each segmented word in the recognition text, so that error detection bases are various, and error detection accuracy can be improved.
Description
technical field [0001] Embodiments of the present invention relate to the technical field of language processing, and more specifically, to a method and device for error detection of recognized text. Background technique [0002] At present, language communication has become an important issue faced by different ethnic groups when they communicate with each other. Traditional translation methods usually use human escort interpretation, consecutive interpretation, and simultaneous interpretation to solve the problem of language communication barriers. However, due to insufficient manpower and cost constraints, they cannot meet the needs of ordinary people for communication. The development of speech translation technology has made a useful supplement to traditional translation methods, providing another way for ordinary people to communicate in daily life, and has more advantages in terms of cost and timeliness. Speech translation includes three steps: speech recognition, ma...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/28G06F17/27
CPCG06F40/284G06F40/44G06F40/58
Inventor 刘俊华魏思胡国平柳林王建社方昕李永超孟廷
Owner 新疆声谷融创数字产业发展有限公司