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

Method and system for detecting unsmooth phenomenon in voice translation system

A voice translation and fluency technology, applied in natural language translation, semantic analysis, natural language data processing, etc., can solve the problem of unsmooth spoken text and achieve the effect of convenient processing

Pending Publication Date: 2020-03-03
BEIJING ZIDONG COGNITIVE TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, the text recognized by these speech signals through the speech recognition system is very different from the standardized written text, and the machine translation system based on written text training will encounter many problems when processing spoken text, mainly reflected in the fact that the spoken text is still There are many disfluency factors

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 system for detecting unsmooth phenomenon in voice translation system
  • Method and system for detecting unsmooth phenomenon in voice translation system
  • Method and system for detecting unsmooth phenomenon in voice translation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] refer to figure 1 , figure 1 It is a flowchart of a method for detecting disfluency in a speech translation system provided by an embodiment of the present invention, and the method includes:

[0068] S101. Obtain source text data to be detected;

[0069] The source text data is text data obtained by the speech recognition device, such as transcription data of speeches and conferences.

[0070] S102. Perform preprocessing and vectorization processing on the source text data to obtain a word vector sequence of each sentence source text data;

[0071] The preprocessing includes: segmenting the source text data by characters, extracting the bigram and trigram features of the source text data, and extracting the prosody features according to the speech signal corresponding to the source text data. The feature extraction in the preprocessing can use the existing technology, such as modeling based on the support vector machine, etc., and the vectorization processing can al...

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 embodiment of the invention provides a method and system for detecting an unsmooth phenomenon in a voice translation system. The unsmooth phenomenon in the to-be-detected source text data is marked through the trained unsmooth detection model, and the unsmooth text data is converted into smooth target text data more suitable for written expression from the semantic level, so that the unsmoothtarget text data better conforms to the expression habit of written language, and processing of a downstream machine translation task is more convenient.

Description

technical field [0001] The invention relates to the fields of natural language processing and speech signal processing, in particular to a method and system for detecting disfluency in a speech translation system. Background technique [0002] As a technology that converts voice signals into text signals, the voice signal system is an important part of smart terminals in the mobile Internet era. With the integration of the world, language has gradually become a major obstacle preventing people from different countries from obtaining real-time information, so voice translation came into being. [0003] The structure of a typical speech translation system consists of a speech recognition module, a machine translation module, and a speech synthesis module. Usually, the text recognized by these speech signals through the speech recognition system is very different from the standardized written text, and the machine translation system based on written text training will encounte...

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): G06F40/205G06F40/289G06F40/30G06F40/253G06F40/58
CPCY02D10/00
Inventor 王峰
Owner BEIJING ZIDONG COGNITIVE 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