Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Dialectal context multi-language translation method

A multi-language and dialect technology, applied in natural language translation, speech analysis, speech recognition, etc., can solve the problems of inaccurate translation of dialects, increase the mistranslation rate, etc., achieve fast computing speed, reduce mistranslation rate, and improve application range effect

Inactive Publication Date: 2017-10-13
SICHUAN XINYIMAI TECH CO LTD
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to: solve the problem that the language translation tools in the prior art cannot accurately translate dialects and increase the mistranslation rate of translation, and provide a multilingual translation method in dialect context

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
  • Dialectal context multi-language translation method
  • Dialectal context multi-language translation method
  • Dialectal context multi-language translation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment adopts the English model voice "This is a test sample for myself" spoken by Americans. The sampling frequency is 11025Hz, the sampling depth is 16bit, mono, and the duration is 2.157 seconds. Actual analysis of time-domain diagrams, spectrogram formants, pitch period diagrams, and sound intensity diagrams, such as Figure 4 Shown; extract formant, pitch period characteristic, MFCC and LPCC parameter characteristic code carry out redundantly after carrying out the probability distribution statistics of dialect speech characteristic code to dialect voice file, will have the code of characteristic code element and adopt compression mode to re-encode as The characteristic code of the 64-byte dialect voice, the characteristic code is assigned the retrieval number and compiled into the characteristic code database, that is, compiled into the spectrum characteristic code database.

Embodiment 2

[0064] This embodiment adopts the English model voice "This is a test sample for myself" spoken by the British. The sampling frequency is 11025Hz, the sampling depth is 16bit, mono, and the duration is 2.267 seconds. Actual analysis of time-domain diagrams, spectrogram formants, pitch period diagrams, and sound intensity diagrams, such as Figure 5 Shown; extract formant, pitch period characteristic, MFCC and LPCC parameter characteristic code carry out redundantly after carrying out the probability distribution statistics of dialect speech characteristic code to dialect voice file, will have the code of characteristic code element and adopt compression mode to re-encode as The characteristic code of the dialect of 64 bytes, the characteristic code is assigned the search number and compiled into the characteristic code database, that is, compiled into the frequency spectrum characteristic code database.

Embodiment 3

[0066] In this embodiment, Indians speak the English model voice "This is a test sample for myself". The sampling frequency is 11025Hz, the sampling depth is 16bit, mono, and the duration is 1.956 seconds. Actual analysis of time-domain diagrams, spectrogram formants, pitch period diagrams, and sound intensity diagrams, such as Figure 6 Shown; extract formant, pitch period characteristic, MFCC and LPCC parameter characteristic code carry out redundantly after carrying out the probability distribution statistics of dialect speech characteristic code to dialect voice file, will have the code of characteristic code element and adopt compression mode to re-encode as The characteristic code of the 64-byte dialect voice, the characteristic code is assigned the retrieval number and compiled into the characteristic code database, that is, compiled into the spectrum characteristic code database.

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 discloses a dialectal context multi-language translation method, belongs to the computer language translation technology field and solves a problem that an error translation rate increases as a language translation tool in the prior art can not accurately translate dialects. The method comprises steps that step 1, a characteristic code database formed by characteristic codes of various types of dialect voices under a native language system is established; step 2, dialect characteristic compensation codes are generated according to difference between the characteristic codes and standard base voice characteristic codes, and a characteristic compensation code database is formed; step 3, the characteristic compensation codes and corresponding source voices are compounded to generate standard base voices under the native language system; and step 4, the standard base voices are converted into voices or texts of a target language. The method is applied to translation of dialects and customized voices.

Description

technical field [0001] A multilingual translation system and method in a dialect context, used for translation of dialects and personalized voices, belongs to the technical field of computer language translation. Background technique [0002] In the exchanges of culture, economy, military and other fields of various countries in the world, language communication is particularly important. In order to accurately express the meaning of the two languages, human translation has been mainly used in various foreign affairs exchanges for a long time. In recent years, with the rapid development of computer and digital technology, great progress has been made in translation work with computer and digital technology. Various excellent computer translation systems are emerging, especially in text translation. However, in simultaneous translation with a computer translation system, the mistranslation rate is high due to the large number of dialects in each native language family and the...

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
IPC IPC(8): G10L15/02G10L15/04G10L15/06G06F17/28
CPCG06F40/58G10L15/02G10L15/04G10L15/06
Inventor 李伊甸戴沛景
Owner SICHUAN XINYIMAI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com