Method for correcting error-prone words in voice interaction

A technology of voice interaction and calibration method, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of large vocabulary network optimization, omission of typo-prone calibration technology, etc., so as to improve the recognition accuracy and enhance typo-prone correction. ability, the effect of improving driving safety

Inactive Publication Date: 2017-10-31
SHANGHAI JIAO TONG UNIV
View PDF7 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this technology does not optimize large vocabulary networks, such as semantic enh...

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 for correcting error-prone words in voice interaction
  • Method for correcting error-prone words in voice interaction
  • Method for correcting error-prone words in voice interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0056] The invention proposes a series of typo-prone calibration technologies in voice interaction, applies the natural language understanding method to the calibration and correction of typo-prone characters in voice interaction, and realizes a comprehensive system for correcting typo-prone characters in voice interaction. The system includes the following functions:

[0057] First, context-based semantic enhancement. In several specific contexts, the system perceives and recognizes the topic context ...

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 for correcting error-prone words in voice interaction. The method comprises the steps of context recognition, automatic error correction based on semantic restriction, and artificial error correction based on semantic feedback. Through voice interaction with users and perception and recognition of the context of a topic, automatic error correction of an entity with a specific meaning can be achieved by using the named entity recognition technology within the limited semantic range, additional semantics can be obtained through artificial feedback so as to conduct error correction, and higher input efficiency and more convenient wrong word correction than existing voice recognition software are realized.

Description

technical field [0001] The present invention relates to typo-prone calibration technology, in particular, to a method for calibrating typo-prone characters in voice interaction, especially applying the natural language understanding method to the calibration and correction of typo-prone characters in voice interaction, realizing a usable calibration of typo-prone characters in voice interaction Program. Background technique [0002] As a new way of human-computer interaction, voice interaction has been widely used in recent years. This first stems from the development of speech recognition technology, from Hidden Markov Model (HMM), Gaussian Mixture Model (GMM) to the current Deep Neural Network (DNN), speech recognition The error rate of the system has dropped significantly; secondly, the usage habits of smart device users have not yet formed, and new technologies such as voice interaction are easy to be accepted by the public; and the extraordinary development of cloud co...

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): G10L15/22G10L15/18
CPCG10L15/1815G10L15/1822G10L15/22G10L2015/228
Inventor 黄亦睿刘功申苏波刘春梅李建华
Owner SHANGHAI JIAO TONG UNIV
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