Method and device for creating language databases and language translation method and device

A language translation and database technology, applied in the language translation method and device, and the establishment of language databases, can solve the problems of large data storage and calculation amount, and achieve the effect of small data amount and calculation amount, simple method and easy recording.

Inactive Publication Date: 2017-04-26
BYD CO LTD
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the defects of the large amount of data storage and calculation in the translation method in the prior art, thereby providing a method for establishing a language database and a language translation method and device

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for creating language databases and language translation method and device
  • Method and device for creating language databases and language translation method and device
  • Method and device for creating language databases and language translation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] This embodiment provides a method for establishing a language database, which can be used to establish a database required for language translation, can be used for translation between languages ​​in different countries, and can also be used for translation between Mandarin and dialects, such as the first One language can choose Mandarin, and the second language can be a dialect such as Cantonese, such as figure 1 As shown, the method includes the following steps:

[0069] S11. Assign a first index to each first phonetic unit in the first language respectively.

[0070] The speech unit here is the speech signal of a single pronunciation unit or the speech signal of a fixed phrase. A single pronunciation generally corresponds to a word in Chinese, which is a smallest segment of the language, so the speech unit here corresponds to the basic unit of the pronunciation , but there are also some fixed phrases that cannot be divided, so these special sentences or phrases are ...

Embodiment 2

[0084] The present embodiment provides a method of using the language database established in embodiment 1 to translate the first language into a second language, wherein the first language is Mandarin, the second language is a dialect, and the second language in this scheme is A specific dialect, the flow diagram is as follows Figure 5 shown, including the following steps:

[0085] S21. Obtain the input Mandarin voice information, and input it through an input device such as a microphone. For example, the user inputs a section of Mandarin Chinese that needs to be translated through a voice input device.

[0086] S22. Divide the speech information into a plurality of speech units to be translated.

[0087] Firstly, the input Mandarin is subjected to noise reduction processing by cutting the front and back tail sounds, and then the speech segmentation is carried out, and is divided into basic speech units as the speech units to be translated.

[0088] S23. Match the speech ...

Embodiment 3

[0100] This embodiment provides a method for using the language database in Embodiment 1 to translate the second language into the first language, the flow chart is as follows Figure 6 As shown, wherein, the second language is a dialect, and the first language is Mandarin, including the following steps:

[0101] S31. Acquire input voice information in the second language.

[0102] First, obtain the input dialect information, and input it through an input device such as a mobile phone mic or a microphone.

[0103] S32. Split the speech information into multiple speech units to be translated.

[0104] The same as the speech processing method in Embodiment 2, the input Mandarin is first subjected to noise reduction processing by cutting the front and back tail sounds, and then performs speech segmentation, and is divided into basic speech units one by one as the speech units to be translated.

[0105] S33. Match the speech unit to be translated with the second speech unit in t...

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

No PUM Login to view more

Abstract

The invention provides a method and device for creating language databases. The method comprises following steps: respectively distributing a first index to each first voice unit of first language; respectively establishing corresponding relations among phonetic symbols of a first voice unit corresponding to each first index; respectively distributing a second index to each second voice unit of second language; and respectively establishing corresponding relations among phonetic symbols of a second voice unit corresponding to each second index, establishing corresponding relations among phonetic symbols of the first voice unit corresponding to each second video unit corresponding to each second index. Therefore, video units of the first language correspond to the video units of the second language, thereby achieving conversion between the first language and the second language. The method and device for creating language databases are especially adapted to translation among Mandarin and dialects.

Description

technical field [0001] The invention relates to the field of translation, in particular to a method for establishing a language database and a language translation method and device. Background technique [0002] With the development of speech technology, the application of speech recognition technology is becoming more and more extensive, such as convenient applications such as man-machine dialogue and natural language retrieval. At present, Siri of iphone and Google Voice search of Google are the ones that support voice recognition and have relatively mature technology. Both of these methods process the sound into a digital signal or spectrum and transmit it to the Internet Service Provider (SIP). The mode adopted is "local speech recognition + cloud computing service". Integrates natural language processing, user intent analysis and task control, etc. [0003] The cloud computing model refers to computing and processing with the help of servers in the cloud, which can g...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06F17/28
CPCG06F16/21G06F16/2264G06F40/58
Inventor 张松
Owner BYD CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap