Text error correction method and device, computer readable storage medium and terminal equipment

A text error correction and terminal equipment technology, applied in computer parts, computing, voice analysis, etc., can solve the problem of low error correction accuracy and achieve the effect of improving error correction accuracy

Pending Publication Date: 2020-11-27
TCL CORPORATION
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, an embodiment of the present invention provides a text error correction method, device, computer-readable storage medium, and terminal equipment to solve the problem of low error correction accuracy in existing ASR text error correction methods

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
  • Text error correction method and device, computer readable storage medium and terminal equipment
  • Text error correction method and device, computer readable storage medium and terminal equipment
  • Text error correction method and device, computer readable storage medium and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0072] Example 1: When the user opens the iQiyi app, Youku app and other film and television apps, the voice input "wo xiang zhaolang ya bang", after ASR recognition, "I want to find a mace". Through the above method to process "I want to find a mace" and its context information, the classification r can be obtained as a movie scene.

example 2

[0073] Example 2: When a user opens a map app such as Baidu Maps app and Gaode Maps app, the voice input "wo yaozhao lang ya bang", and after ASR recognition, the user gets "I'm looking for a mace". Through the above method to process "I'm looking for a mace" and its context information, the classification r can be obtained as a regional scene.

[0074] Step S103: Determine a puzzle set of the first text data according to the usage scenario.

[0075] In this embodiment, a traditional machine learning language model method can be used to construct a confusion set, which is a set composed of various possible candidate values ​​of words in the first text data. This step is mainly divided into two parts: building a language model and building a puzzle set. Use the built language model to identify and extract the wrong words in the ASR recognition results, and use the classification number n of the scene classification module to construct the corresponding n puzzle sets. Each puzzle se...

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 belongs to the technical field of speech recognition, and particularly relates to a text error correction method and device, a computer readable storage medium and terminal equipment. The method comprises steps of obtaining first text data, wherein the first text data is text data output after preset terminal equipment performs voice recognition on input voice; determining a usage scenario of the first text data according to the current state of the terminal device, the first text data and context information of the first text data; determining a confusion set of the first text data according to the usage scenario; performing error correction processing on the first text data by using a preset deep learning model and an iterative learning model to obtain second text data; andperforming optimization processing on the second text data according to the confusion set to obtain third text data. According to the method, based on methods of deep learning, iterative learning andthe like, different error correction is carried out on the error text according to different scenes, so error correction accuracy is greatly improved.

Description

Technical field [0001] The invention belongs to the technical field of speech recognition, and particularly relates to a text error correction method, device, computer readable storage medium and terminal equipment. Background technique [0002] Artificial intelligence and AI technologies have developed rapidly, and voice interaction methods have appeared on all kinds of smart terminal devices, but they cannot meet the needs of users. The root cause is that the Automatic Speech Recognition (ASR) method does not work well, so the ASR text error correction method appears. The current ASR text error correction method can complete fixed error correction in some simple scenarios. For example, you can correct "I want to order music" to "I want to listen to music", and "I want to match my eyes" to "I want to match my eyes". "Glasses" and so on, but the current ASR text error correction method does not consider that the same sentence has different error correction tasks in different con...

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): G10L15/10G10L15/22G10L15/26G10L15/183G06F40/289G06K9/62
CPCG10L15/10G10L15/22G10L15/26G10L15/183G06F18/24
Inventor 毛俊峰李靖阳郭泽
Owner TCL CORPORATION
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